How do typological properties such as word order and morphological case marking affect the ability of neural sequence models to acquire the syntax of a language? Cross-linguistic comparisons of RNNs’ syntactic performance (e.g., on subject-verb agreement prediction) are complicated by the fact that any two languages differ in multiple typological properties, as well as by differences in training corpus. We propose a paradigm that addresses these issues: we create synthetic versions of English, which differ from English in a single typological parameter, and generate corpora for those languages based on a parsed English corpus. We report a series of experiments in which RNNs were trained to predict agreement features for verbs in each of those synthetic languages. Among other findings, (1) performance was higher in subject-verb-object order (as in English) than in subject-object-verb order (as in Japanese), suggesting that RNNs have a recency bias; (2) predicting agreement with both subject and object (polypersonal agreement) improves over predicting each separately, suggesting that underlying syntactic knowledge transfers across the two tasks; and (3) overt morphological case makes agreement prediction significantly easier, regardless of word order.
http://arxiv.org/abs/1903.06400
We propose a grounded dialogue state encoder which addresses a foundational issue on how to integrate visual grounding with dialogue system components. As a test-bed, we focus on the GuessWhat?! game, a two-player game where the goal is to identify an object in a complex visual scene by asking a sequence of yes/no questions. Our visually-grounded encoder leverages synergies between guessing and asking questions, as it is trained jointly using multi-task learning. We further enrich our model via a cooperative learning regime. We show that the introduction of both the joint architecture and cooperative learning lead to accuracy improvements over the baseline system. We compare our approach to an alternative system which extends the baseline with reinforcement learning. Our in-depth analysis shows that the linguistic skills of the two models differ dramatically, despite approaching comparable performance levels. This points at the importance of analyzing the linguistic output of competing systems beyond numeric comparison solely based on task success.
http://arxiv.org/abs/1809.03408
Generative Adversarial Networks (GANs) have been widely used for the image-to-image translation task. While these models rely heavily on the labeled image pairs, recently some GAN variants have been proposed to tackle the unpaired image translation task. These models exploited supervision at the domain level with a reconstruction process for unpaired image translation. On the other hand, parallel works have shown that leveraging perceptual loss functions based on high level deep features could enhance the generated image quality. Nevertheless, as these GAN-based models either depended on the pretrained deep network structure or relied on the labeled image pairs, they could not be directly applied to the unpaired image translation task. Moreover, despite the improvement of the introduced perceptual losses from deep neural networks, few researchers have explored the possibility of improving the generated image quality from classical image quality measures. To tackle the above two challenges, in this paper, we propose a unified quality-aware GAN-based framework for unpaired image-to-image translation, where a quality-aware loss is explicitly incorporated by comparing each source image and the reconstructed image at the domain level. Specifically, we design two detailed implementations of the quality loss. The first method is based on a classical image quality assessment measure by defining a classical quality-aware loss. The second method proposes an adaptive deep network based loss. Finally, extensive experimental results on many real-world datasets clearly show the quality improvement of our proposed framework, and the superiority of leveraging classical image quality measures for unpaired image translation compared to the deep network based model.
http://arxiv.org/abs/1903.06399
Depth estimation is an important capability for autonomous vehicles to understand and reconstruct 3D environments as well as avoid obstacles during the execution. Accurate depth sensors such as LiDARs are often heavy, expensive and can only provide sparse depth while lighter depth sensors such as stereo cameras are noiser in comparison. We propose an end-to-end learning algorithm that is capable of using sparse, noisy input depth for refinement and depth completion. Our model also produces the camera pose as a byproduct, making it a great solution for autonomous systems. We evaluate our approach on both indoor and outdoor datasets. Empirical results show that our method performs well on the KITTI~\cite{kitti_geiger2012we} dataset when compared to other competing methods, while having superior performance in dealing with sparse, noisy input depth on the TUM~\cite{sturm12iros} dataset.
http://arxiv.org/abs/1903.06397
Object detection is an integral part of an autonomous vehicle for its safety-critical and navigational purposes. Traffic signs as objects play a vital role in guiding such systems. However, if the vehicle fails to locate any critical sign, it might make a catastrophic failure. In this paper, we propose an approach to identify traffic signs that have been mistakenly discarded by the object detector. The proposed method raises an alarm when it discovers a failure by the object detector to detect a traffic sign. This approach can be useful to evaluate the performance of the detector during the deployment phase. We trained a single shot multi-box object detector to detect traffic signs and used its internal features to train a separate false negative detector (FND). During deployment, FND decides whether the traffic sign detector (TSD) has missed a sign or not. We are using precision and recall to measure the accuracy of FND in two different datasets. For 80% recall, FND has achieved 89.9% precision in Belgium Traffic Sign Detection dataset and 90.8% precision in German Traffic Sign Recognition Benchmark dataset respectively. To the best of our knowledge, our method is the first to tackle this critical aspect of false negative detection in robotic vision. Such a fail-safe mechanism for object detection can improve the engagement of robotic vision systems in our daily life.
http://arxiv.org/abs/1903.06391
A simple prior free factorization algorithm \cite{dai2014simple} is quite often cited work in the field of Non-Rigid Structure from Motion (NRSfM). The benefit of this work lies in its simplicity of implementation, strong theoretical justification to the motion and structure estimation, and its invincible originality. Despite this, the prevailing view is, that it performs exceedingly inferior to other methods on several benchmark datasets \cite{jensen2018benchmark,akhter2009nonrigid}. However, our subtle investigation provides some empirical statistics which made us think against such views. The statistical results we obtained supersedes Dai {\it{et al.}}\cite{dai2014simple} originally reported results on the benchmark datasets by a significant margin under some elementary changes in their core algorithmic idea \cite{dai2014simple}. Now, these results not only exposes some unrevealed areas for research in NRSfM but also give rise to new mathematical challenges for NRSfM researchers. We argue that by \textbf{properly} utilizing the well-established assumptions about a non-rigidly deforming shape i.e, it deforms smoothly over frames and it spans a low-rank space, the simple prior-free idea can provide results which is comparable to the best available algorithms. In this paper, we explore some of the hidden intricacies missed by Dai {\it{et. al.}} work \cite{dai2014simple} and how some elementary measures and modifications can enhance its performance, as high as 18\% on the benchmark dataset. The improved performance is justified and empirically verified by extensive experiments on several datasets. We believe our work has both practical and theoretical importance for the development of better NRSfM algorithms.
http://arxiv.org/abs/1902.10274
Human-object interactions (HOI) recognition and pose estimation are two closely related tasks. Human pose is an essential cue for recognizing actions and localizing the interacted objects. Meanwhile, human action and their interacted objects’ localizations provide guidance for pose estimation. In this paper, we propose a turbo learning framework to perform HOI recognition and pose estimation simultaneously. First, two modules are designed to enforce message passing between the tasks, i.e. pose aware HOI recognition module and HOI guided pose estimation module. Then, these two modules form a closed loop to utilize the complementary information iteratively, which can be trained in an end-to-end manner. The proposed method achieves the state-of-the-art performance on two public benchmarks including Verbs in COCO (V-COCO) and HICO-DET datasets.
http://arxiv.org/abs/1903.06355
Over four decades, the majority addresses the problem of optical flow estimation using variational methods. With the advance of machine learning, some recent works have attempted to address the problem using convolutional neural network (CNN) and have showed promising results. FlowNet2, the state-of-the-art CNN, requires over 160M parameters to achieve accurate flow estimation. Our LiteFlowNet2 outperforms FlowNet2 on Sintel and KITTI benchmarks, while being 25.3 times smaller in the footprint and 3.1 times faster in the running speed. LiteFlowNet2 which is built on the foundation laid by conventional methods has marked a milestone to achieve the corresponding roles as data fidelity and regularization in variational methods. We present an effective flow inference approach at each pyramid level through a novel lightweight cascaded network. It provides high flow estimation accuracy through early correction with seamless incorporation of descriptor matching. A novel flow regularization layer is used to ameliorate the issue of outliers and vague flow boundaries through a novel feature-driven local convolution. Our network also owns an effective structure for pyramidal feature extraction and embraces feature warping rather than image warping as practiced in FlowNet2. Comparing to our earlier work, LiteFlowNet2 improves the optical flow accuracy on Sintel clean pass by 24%, Sintel final pass by 8.9%, KITTI 2012 by 16.8%, and KITTI 2015 by 17.5%. Our network protocol and trained models will be made publicly available on https://github.com/twhui/LiteFlowNet2 .
http://arxiv.org/abs/1903.07414
Over four decades, the majority addresses the problem of optical flow estimation using variational methods. With the advance of machine learning, some recent works have attempted to address the problem using convolutional neural network (CNN) and have showed promising results. FlowNet2, the state-of-the-art CNN, requires over 160M parameters to achieve accurate flow estimation. Our LiteFlowNet2 outperforms FlowNet2 on Sintel and KITTI benchmarks, while being 25.3 times smaller in the footprint and 3.1 times faster in the running speed. LiteFlowNet2 which is built on the foundation laid by conventional methods has marked a milestone to achieve the corresponding roles as data fidelity and regularization in variational methods. We present an effective flow inference approach at each pyramid level through a novel lightweight cascaded network. It provides high flow estimation accuracy through early correction with seamless incorporation of descriptor matching. A novel flow regularization layer is used to ameliorate the issue of outliers and vague flow boundaries through a novel feature-driven local convolution. Our network also owns an effective structure for pyramidal feature extraction and embraces feature warping rather than image warping as practiced in FlowNet2. Comparing to our earlier work, LiteFlowNet2 improves the optical flow accuracy on Sintel clean pass by 24%, Sintel final pass by 8.9%, KITTI 2012 by 16.8%, and KITTI 2015 by 17.5%. Our network protocol and trained models will be made publicly available on https://github.com/twhui/LiteFlowNet2 .
http://arxiv.org/abs/1903.07414
Formality style transformation is the task of modifying the formality of a given sentence without changing its content. Its challenge is the lack of large-scale sentence-aligned parallel data. In this paper, we propose an omnivorous model that takes parallel data and formality-classified data jointly to alleviate the data sparsity issue. We empirically demonstrate the effectiveness of our approach by achieving the state-of-art performance on a recently proposed benchmark dataset of formality transfer. Furthermore, our model can be readily adapted to other unsupervised text style transfer tasks like unsupervised sentiment transfer and achieve competitive results on three widely recognized benchmarks.
http://arxiv.org/abs/1903.06353
The accuracy and robustness of image classification with supervised deep learning are dependent on the availability of large-scale, annotated training data. However, there is a paucity of annotated data available due to the complexity of manual annotation. To overcome this problem, a popular approach is to use transferable knowledge across different domains by: 1) using a generic feature extractor that has been pre-trained on large-scale general images (i.e., transfer-learned) but which not suited to capture characteristics from medical images; or 2) fine-tuning generic knowledge with a relatively smaller number of annotated images. Our aim is to reduce the reliance on annotated training data by using a new hierarchical unsupervised feature extractor with a convolutional auto-encoder placed atop of a pre-trained convolutional neural network. Our approach constrains the rich and generic image features from the pre-trained domain to a sophisticated representation of the local image characteristics from the unannotated medical image domain. Our approach has a higher classification accuracy than transfer-learned approaches and is competitive with state-of-the-art supervised fine-tuned methods.
http://arxiv.org/abs/1903.06342
With the popularity of dual cameras in recently released smart phones, a growing number of super-resolution (SR) methods have been proposed to enhance the resolution of stereo image pairs. However, the lack of high-quality stereo datasets has limited the research in this area. To facilitate the training and evaluation of novel stereo SR algorithms, in this paper, we propose a large-scale stereo dataset named Flickr1024. Compared to the existing stereo datasets, the proposed dataset contains much more high-quality images and covers diverse scenarios. We train two state-of-the-art stereo SR methods (i.e., StereoSR and PASSRnet) on the KITTI2015, Middlebury, and Flickr1024 datasets. Experimental results demonstrate that our dataset can improve the performance of stereo SR algorithms. The Flickr1024 dataset is available online at: https://yingqianwang.github.io/Flickr1024.
http://arxiv.org/abs/1903.06332
Although unsupervised person re-identification (RE-ID) has drawn increasing research attentions due to its potential to address the scalability problem of supervised RE-ID models, it is very challenging to learn discriminative information in the absence of pairwise labels across disjoint camera views. To overcome this problem, we propose a deep model for the soft multilabel learning for unsupervised RE-ID. The idea is to learn a soft multilabel (real-valued label likelihood vector) for each unlabeled person by comparing the unlabeled person with a set of known reference persons from an auxiliary domain. We propose the soft multilabel-guided hard negative mining to learn a discriminative embedding for the unlabeled target domain by exploring the similarity consistency of the visual features and the soft multilabels of unlabeled target pairs. Since most target pairs are cross-view pairs, we develop the cross-view consistent soft multilabel learning to achieve the learning goal that the soft multilabels are consistently good across different camera views. To enable effecient soft multilabel learning, we introduce the reference agent learning to represent each reference person by a reference agent in a joint embedding. We evaluate our unified deep model on Market-1501 and DukeMTMC-reID. Our model outperforms the state-of-theart unsupervised RE-ID methods by clear margins. Code is available at https://github.com/KovenYu/MAR.
http://arxiv.org/abs/1903.06325
This paper proposes a new method for live free-viewpoint human performance capture with dynamic details (e.g., cloth wrinkles) using a single RGBD camera. Our main contributions are: (i) a multi-layer representation of garments and body, and (ii) a physics-based performance capture procedure. We first digitize the performer using multi-layer surface representation, which includes the undressed body surface and separate clothing meshes. For performance capture, we perform skeleton tracking, cloth simulation, and iterative depth fitting sequentially for the incoming frame. By incorporating cloth simulation into the performance capture pipeline, we can simulate plausible cloth dynamics and cloth-body interactions even in the occluded regions, which was not possible in previous capture methods. Moreover, by formulating depth fitting as a physical process, our system produces cloth tracking results consistent with the depth observation while still maintaining physical constraints. Results and evaluations show the effectiveness of our method. Our method also enables new types of applications such as cloth retargeting, free-viewpoint video rendering and animations.
http://arxiv.org/abs/1903.06323
Expert programmers’ eye-movements during source code reading are valuable sources that are considered to be associated with their domain expertise. We advocate a vision of new intelligent systems incorporating expertise of experts for software development tasks, such as issue localization, comment generation, and code generation. We present a conceptual framework of neural autonomous agents based on imitation learning (IL), which enables agents to mimic the visual attention of an expert via his/her eye movement. In this framework, an autonomous agent is constructed as a context-based attention model that consists of encoder/decoder network and trained with state-action sequences generated by an experts’ demonstration. Challenges to implement an IL-based autonomous agent specialized for software development task are discussed in this paper.
http://arxiv.org/abs/1903.06320
Many telepresence robots are equipped with a forward-facing camera for video communication and a downward-facing camera for navigation. In this paper, we propose to stitch videos from the FF-camera with a wide-angle lens and the DF-camera with a fisheye lens for telepresence robots. We aim at providing more compact and efficient visual feedback for the user interface of telepresence robots with user-friendly interactive experiences. To this end, we present a multi-homography-based video stitching method which stitches videos from a wide-angle camera and a fisheye camera. The method consists of video image alignment, seam cutting, and image blending. We directly align the wide-angle video image and the fisheye video image based on the multi-homography alignment without calibration, distortion correction, and unwarping procedures. Thus, we can obtain a stitched video with shape preservation in the non-overlapping regions and alignment in the overlapping area for telepresence. To alleviate ghosting effects caused by moving objects and/or moving cameras during telepresence robot driving, an optimal seam is found for aligned video composition, and the optimal seam will be updated in subsequent frames, considering spatial and temporal coherence. The final stitched video is created by image blending based on the optimal seam. We conducted a user study to demonstrate the effectiveness of our method and the superiority of telepresence robots with a stitched video as visual feedback.
http://arxiv.org/abs/1903.06319
Unsupervised Learning based monocular visual odometry (VO) has lately drawn significant attention for its potential in label-free leaning ability and robustness to camera parameters and environmental variations. However, partially due to the lack of drift correction technique, these methods are still by far less accurate than geometric approaches for large-scale odometry estimation. In this paper, we propose to leverage graph optimization and loop closure detection to overcome limitations of unsupervised learning based monocular visual odometry. To this end, we propose a hybrid VO system which combines an unsupervised monocular VO called NeuralBundler with a pose graph optimization back-end. NeuralBundler is a neural network architecture that uses temporal and spatial photometric loss as main supervision and generates a windowed pose graph consists of multi-view 6DoF constraints. We propose a novel pose cycle consistency loss to relieve the tensions in the windowed pose graph, leading to improved performance and robustness. In the back-end, a global pose graph is built from local and loop 6DoF constraints estimated by NeuralBundler and is optimized over SE(3). Empirical evaluation on the KITTI odometry dataset demonstrates that 1) NeuralBundler achieves state-of-the-art performance on unsupervised monocular VO estimation, and 2) our whole approach can achieve efficient loop closing and show favorable overall translational accuracy compared to established monocular SLAM systems.
http://arxiv.org/abs/1903.06315
Label information is widely used in hashing methods because of its effectiveness of improving the precision. The existing hashing methods always use two different projections to represent the mutual regression between hash codes and class labels. In contrast to the existing methods, we propose a novel learning-based hashing method termed stable supervised discrete hashing with mutual linear regression (S2DHMLR) in this study, where only one stable projection is used to describe the linear correlation between hash codes and corresponding labels. To the best of our knowledge, this strategy has not been used for hashing previously. In addition, we further use a boosting strategy to improve the final performance of the proposed method without adding extra constraints and with little extra expenditure in terms of time and space. Extensive experiments conducted on three image benchmarks demonstrate the superior performance of the proposed method.
http://arxiv.org/abs/1904.00744
Robots that are trained to perform a task in a fixed environment often fail when facing unexpected changes to the environment due to a lack of exploration. We propose a principled way to adapt the policy for better exploration in changing sparse-reward environments. Unlike previous works which explicitly model environmental changes, we analyze the relationship between the value function and the optimal exploration for a Gaussian-parameterized policy and show that our theory leads to an effective strategy for adjusting the variance of the policy, enabling fast adapt to changes in a variety of sparse-reward environments.
http://arxiv.org/abs/1903.06309
We propose a novel framework for Deep Reinforcement Learning (DRL) in modular robotics that provides an approach which trains a robot directly from joint states, using traditional robotic tools. We use an state-of-the-art implementation of the Proximal Policy Optimization, Trust Region Policy Optimization and Actor-Critic Kronecker-Factored Trust Region algorithms to learn policies in four different Modular Articulated Robotic Arm (MARA) environments. We support this process using a framework that communicates with typical tools used in robotics, such as Gazebo and Robot Operating System 2 (ROS 2). We compare the robustness of the performance of such methods in modular robots with an empirical study in simulation.
http://arxiv.org/abs/1903.06282
As machine learning (ML) systems have advanced, they have acquired more power over humans’ lives, and questions about what values are embedded in them have become more complex and fraught. It is conceivable that in the coming decades, humans may succeed in creating artificial general intelligence (AGI) that thinks and acts with an open-endedness and autonomy comparable to that of humans. The implications would be profound for our species; they are now widely debated not just in science fiction and speculative research agendas but increasingly in serious technical and policy conversations. Much work is underway to try to weave ethics into advancing ML research. We think it useful to add the lens of parenting to these efforts, and specifically radical, queer theories of parenting that consciously set out to nurture agents whose experiences, objectives and understanding of the world will necessarily be very different from their parents’. We propose a spectrum of principles which might underpin such an effort; some are relevant to current ML research, while others will become more important if AGI becomes more likely. These principles may encourage new thinking about the development, design, training, and release into the world of increasingly autonomous agents.
http://arxiv.org/abs/1903.06281
This paper presents an upgraded, real world application oriented version of gym-gazebo, the Robot Operating System (ROS) and Gazebo based Reinforcement Learning (RL) toolkit, which complies with OpenAI Gym. The content discusses the new ROS 2 based software architecture and summarizes the results obtained using Proximal Policy Optimization (PPO). Ultimately, the output of this work presents a benchmarking system for robotics that allows different techniques and algorithms to be compared using the same virtual conditions. We have evaluated environments with different levels of complexity of the Modular Articulated Robotic Arm (MARA), reaching accuracies in the millimeter scale. The converged results show the feasibility and usefulness of the gym-gazebo 2 toolkit, its potential and applicability in industrial use cases, using modular robots.
http://arxiv.org/abs/1903.06278
Humans have an incredible ability to process and understand information from multiple sources such as images, video, text, and speech. Recent success of deep neural networks has enabled us to develop algorithms which give machines the ability to understand and interpret this information. There is a need to both broaden their applicability and develop methods which correlate visual information along with semantic content. We propose a unified model which jointly trains on images and captions, and learns to generate new captions given either an image or a caption query. We evaluate our model on three different tasks namely cross-modal retrieval, image captioning, and sentence paraphrasing. Our model gains insight into cross-modal vector embeddings, generalizes well on multiple tasks and is competitive to state of the art methods on retrieval.
http://arxiv.org/abs/1903.06275
One of the most essential prerequisites behind a successful task execution of a team of agents is to accurately estimate and track their poses. We consider a cooperative multi-agent positioning problem where each agent performs single-agent positioning until it encounters some other agent. Upon the encounter, the two agents measure their relative pose, and exchange particle clouds representing their poses. We propose a cooperative positioning algorithm which fuses the received information with the locally available measurements and infers an agent’s pose within Bayesian framework. The algorithm is scalable to multiple agents, has relatively low computational complexity, admits decentralized implementation across agents, and imposes relatively mild requirements on communication coverage and bandwidth. The experiments indicate that the proposed algorithm considerably improves single-agent positioning accuracy, reduces the convergence time of a particle cloud and, unlike its single-agent positioning counterpart, exhibits immunity to an impeding feature-scarce and symmetric environment layout.
http://arxiv.org/abs/1903.06273
Self-organization can be broadly defined as the ability of a system to display ordered spatio-temporal patterns solely as the result of the interactions among the system components. Processes of this kind characterize both living and artificial systems, making self-organization a concept that is at the basis of several disciplines, from physics to biology to engineering. Placed at the frontiers between disciplines, Artificial Life (ALife) has heavily borrowed concepts and tools from the study of self-organization, providing mechanistic interpretations of life-like phenomena as well as useful constructivist approaches to artificial system design. Despite its broad usage within ALife, the concept of self-organization has been often excessively stretched or misinterpreted, calling for a clarification that could help with tracing the borders between what can and cannot be considered self-organization. In this review, we discuss the fundamental aspects of self-organization and list the main usages within three primary ALife domains, namely “soft” (mathematical/computational modeling), “hard” (physical robots), and “wet” (chemical/biological systems) ALife. Finally, we discuss the usefulness of self-organization within ALife studies, point to perspectives for future research, and list open questions.
http://arxiv.org/abs/1903.07456
Finding the best neural network architecture requires significant time, resources, and human expertise. These challenges are partially addressed by neural architecture search (NAS) which is able to find the best convolutional layer or cell that is then used as a building block for the network. However, once a good building block is found, manual design is still required to assemble the final architecture as a combination of multiple blocks under a predefined parameter budget constraint. A common solution is to stack these blocks into a single tower and adjust the width and depth to fill the parameter budget. However, these single tower architectures may not be optimal. Instead, in this paper we present the AdaNAS algorithm, that uses ensemble techniques to compose a neural network as an ensemble of smaller networks automatically. Additionally, we introduce a novel technique based on knowledge distillation to iteratively train the smaller networks using the previous ensemble as a teacher. Our experiments demonstrate that ensembles of networks improve accuracy upon a single neural network while keeping the same number of parameters. Our models achieve comparable results with the state-of-the-art on CIFAR-10 and sets a new state-of-the-art on CIFAR-100.
https://arxiv.org/abs/1903.06236
This paper addresses the problem of single image depth estimation (SIDE), focusing on improving the accuracy of deep neural network predictions. In a supervised learning scenario, the quality of predictions is intrinsically related to the training labels, which guide the optimization process. For indoor scenes, structured-light-based depth sensors (e.g. Kinect) are able to provide dense, albeit short-range, depth maps. On the other hand, for outdoor scenes, LiDARs are still considered the standard sensor, which comparatively provide much sparser measurements, especially in areas further away. Rather than modifying the neural network structure to deal with sparse depth maps, this paper introduces a novel technique for the densification of depth maps based on the Hilbert Maps framework. A continuous occupancy map is produced based on 3D points from LiDAR scans, and the resulting reconstructed surface is projected into a 2D depth map with arbitrary resolution. Experiments conducted with various subsets of the KITTI dataset show the improvement produced by the proposed Sparse-to-Continuous technique, without the introduction of extra information into the training methodology.
http://arxiv.org/abs/1809.09061
In this paper, we propose a method for obtaining sentence-level embeddings. While the problem of securing word-level embeddings is very well studied, we propose a novel method for obtaining sentence-level embeddings. This is obtained by a simple method in the context of solving the paraphrase generation task. If we use a sequential encoder-decoder model for generating paraphrase, we would like the generated paraphrase to be semantically close to the original sentence. One way to ensure this is by adding constraints for true paraphrase embeddings to be close and unrelated paraphrase candidate sentence embeddings to be far. This is ensured by using a sequential pair-wise discriminator that shares weights with the encoder that is trained with a suitable loss function. Our loss function penalizes paraphrase sentence embedding distances from being too large. This loss is used in combination with a sequential encoder-decoder network. We also validated our method by evaluating the obtained embeddings for a sentiment analysis task. The proposed method results in semantic embeddings and outperforms the state-of-the-art on the paraphrase generation and sentiment analysis task on standard datasets. These results are also shown to be statistically significant.
http://arxiv.org/abs/1806.00807
We consider the recently proposed reinforcement learning (RL) framework of Contextual Markov Decision Processes (CMDP), where the agent has a sequence of episodic interactions with tabular environments chosen from a possibly infinite set. The parameters of these environments depend on a context vector that is available to the agent at the start of each episode. In this paper, we propose a no-regret online RL algorithm in the setting where the MDP parameters are obtained from the context using generalized linear models (GLMs). The proposed algorithm \texttt{GL-ORL} relies on efficient online updates and is also memory efficient. Our analysis of the algorithm gives new results in the logit link case and improves previous bounds in the linear case. Our algorithm uses efficient Online Newton Step updates to build confidence sets. Moreover, for any strongly convex link function, we also show a generic conversion from any online no-regret algorithm to confidence sets.
http://arxiv.org/abs/1903.06187
Deep Reinforcement Learning has enabled the control of increasingly complex and high-dimensional problems. However, the need of vast amounts of data before reasonable performance is attained prevents its widespread application. We employ binary corrective feedback as a general and intuitive manner to incorporate human intuition and domain knowledge in model-free machine learning. The uncertainty in the policy and the corrective feedback is combined directly in the action space as probabilistic conditional exploration. As a result, the greatest part of the otherwise ignorant learning process can be avoided. We demonstrate the proposed method, Predictive Probabilistic Merging of Policies (PPMP), in combination with DDPG. In experiments on continuous control problems of the OpenAI Gym, we achieve drastic improvements in sample efficiency, final performance, and robustness to erroneous feedback, both for human and synthetic feedback. Additionally, we show solutions beyond the demonstrated knowledge.
http://arxiv.org/abs/1903.06151
Learning subtle yet discriminative features (e.g., beak and eyes for a bird) plays a significant role in fine-grained image recognition. Existing attention-based approaches localize and amplify significant parts to learn fine-grained details, which often suffer from a limited number of parts and heavy computational cost. In this paper, we propose to learn such fine-grained features from hundreds of part proposals by Trilinear Attention Sampling Network (TASN) in an efficient teacher-student manner. Specifically, TASN consists of 1) a trilinear attention module, which generates attention maps by modeling the inter-channel relationships, 2) an attention-based sampler which highlights attended parts with high resolution, and 3) a feature distiller, which distills part features into a global one by weight sharing and feature preserving strategies. Extensive experiments verify that TASN yields the best performance under the same settings with the most competitive approaches, in iNaturalist-2017, CUB-Bird, and Stanford-Cars datasets.
http://arxiv.org/abs/1903.06150
LiDAR-camera calibration is a precondition for many heterogeneous systems that fuse data from LiDAR and camera. However, the constraint from the common field of view and the requirement for strict time synchronization make the calibration a challenging problem. In this paper, we propose a hybrid LiDAR-camera calibration method aiming to solve these two difficulties. The configuration between LiDAR and camera is free from their common field of view as we move the camera to cover the scenario observed by LiDAR. 3D visual reconstruction of the environment can be achieved from the sequential visual images obtained by the moving camera, which later can be aligned with the single 3D laser scan captured when both the scene and the equipment are stationary. Under this design, our method can further get rid of the influence from time synchronization between LiDAR and camera. Moreover, the extended field of view obtained by the moving camera can improve the calibration accuracy. We derive the conditions of minimal observability for our method and discuss the influence on calibration accuracy from different placements of chessboards, which can be utilized as a guideline for designing high-accuracy calibration procedures. We validate our method on both simulation platform and real-world datasets. Experiments show that our method can achieve higher accuracy than other comparable methods.
http://arxiv.org/abs/1903.06141
We introduce the Tucker Tensor Layer (TTL), an alternative to the dense weight-matrices of the fully connected layers of feed-forward neural networks (NNs), to answer the long standing quest to compress NNs and improve their interpretability. This is achieved by treating these weight-matrices as the unfolding of a higher order weight-tensor. This enables us to introduce a framework for exploiting the multi-way nature of the weight-tensor in order to efficiently reduce the number of parameters, by virtue of the compression properties of tensor decompositions. The Tucker Decomposition (TKD) is employed to decompose the weight-tensor into a core tensor and factor matrices. We re-derive back-propagation within this framework, by extending the notion of matrix derivatives to tensors. In this way, the physical interpretability of the TKD is exploited to gain insights into training, through the process of computing gradients with respect to each factor matrix. The proposed framework is validated on synthetic data and on the Fashion-MNIST dataset, emphasizing the relative importance of various data features in training, hence mitigating the “black-box” issue inherent to NNs. Experiments on both MNIST and Fashion-MNIST illustrate the compression properties of the TTL, achieving a 66.63 fold compression whilst maintaining comparable performance to the uncompressed NN.
http://arxiv.org/abs/1903.06133
In this paper we propose a deep residual autoencoder exploiting Residual-in-Residual Dense Blocks (RRDB) to remove artifacts in JPEG compressed images that is independent from the Quality Factor (QF) used. The proposed approach leverages both the learning capacity of deep residual networks and prior knowledge of the JPEG compression pipeline. The proposed model operates in the YCbCr color space and performs JPEG artifact restoration in two phases using two different autoencoders: the first one restores the luma channel exploiting 2D convolutions; the second one, using the restored luma channel as a guide, restores the chroma channels explotining 3D convolutions. Extensive experimental results on three widely used benchmark datasets (i.e. LIVE1, BDS500, and CLASSIC-5) show that our model is able to outperform the state of the art with respect to all the evaluation metrics considered (i.e. PSNR, PSNR-B, and SSIM). This results is remarkable since the approaches in the state of the art use a different set of weights for each compression quality, while the proposed model uses the same weights for all of them, making it applicable to images in the wild where the QF used for compression is unkwnown. Furthermore, the proposed model shows a greater robustness than state-of-the-art methods when applied to compression qualities not seen during training.
http://arxiv.org/abs/1903.06117
In this work, we address the estimation, planning, control and mapping problems to allow a small quadrotor to autonomously inspect the interior of hazardous damaged nuclear sites. These algorithms run onboard on a computationally limited CPU. We investigate the effect of varying illumination on the system performance. To the best of our knowledge, this is the first fully autonomous system of this size and scale applied to inspect the interior of a full scale mock-up of a Primary Containment Vessel (PCV). The proposed solution opens up new ways to inspect nuclear reactors and to support nuclear decommissioning, which is well known to be a dangerous, long and tedious process. Experimental results with varying illumination conditions show the ability to navigate a full scale mock-up PCV pedestal and create a map of the environment, while concurrently avoiding obstacles.
http://arxiv.org/abs/1903.06111
In this work we present Discrete Attend Infer Repeat (Discrete-AIR), a Recurrent Auto-Encoder with structured latent distributions containing discrete categorical distributions, continuous attribute distributions, and factorised spatial attention. While inspired by the original AIR model andretaining AIR model’s capability in identifying objects in an image, Discrete-AIR provides direct interpretability of the latent codes. We show that for Multi-MNIST and a multiple-objects version of dSprites dataset, the Discrete-AIR model needs just one categorical latent variable, one attribute variable (for Multi-MNIST only), together with spatial attention variables, for efficient inference. We perform analysis to show that the learnt categorical distributions effectively capture the categories of objects in the scene for Multi-MNIST and for Multi-Sprites.
http://arxiv.org/abs/1903.06581
In this paper we study a multi-robot path planning problem for persistent monitoring of an environment. We represent the areas to be monitored as the vertices of a weighted graph. For each vertex, there is a constraint on the maximum time spent by the robots between visits to that vertex, called the latency, and the objective is to find the minimum number of robots that can satisfy these latency constraints. The decision version of this problem is known to be PSPACE-complete. We present a $O(\log \rho)$ approximation algorithm for the problem where $\rho$ is the ratio of the maximum and the minimum latency constraints. We also present an orienteering based heuristic to solve the problem and show through simulations that in most of the cases the heuristic algorithm gives better solutions than the approximation algorithm. We evaluate our algorithms on large problem instances in a patrolling scenario and in a persistent scene reconstruction application. We also compare the algorithms with an existing solver on benchmark instances.
http://arxiv.org/abs/1903.06105
In this paper, the application of 5G communication technology in an industrial environment is discussed. It acts as an enabler for the separation of sensors/actors and resources, like memory and computational power. 5G offers characteristics essential for the proposed approach like robustness, ultra-low latency, high data rates and massive number of devices. A demonstrator of a production line was used as an test environment for 5G in a real-world industrial application. A wide variety of heterogeneous sensor systems is used by a mobile robot platform. The collected data is transmitted via a 5G network to various Cloud systems. The product is treated as a cyber-physical system with a RFID tag in conjunction with the product memory system. The dynamic production flow approach is discussed centered around the robot which is used for transportation and inspection of products. This inspection is performed during the transportation and influences the production flow directly. This is desirable in the scope of Industry 4.0 to have an efficient production down to batch size 1.
http://arxiv.org/abs/1904.01476
Malaria is a life-threatening mosquito-borne blood disease, hence early detection is very crucial for health. The conventional method for the detection is a microscopic examination of Giemsa-stained blood smears, which needs a highly trained skilled technician. Automated classifications of different stages of malaria still a challenging task, especially having poor sensitivity in detecting the early trophozoite and late trophozoite or schizont stage with limited labelled datasize. The study aims to develop a fast, robust and fully automated system for the classification of different stages of malaria with limited data size by using the pre-trained convolutional neural networks (CNNs) as a classifier and multi-wavelength to increase the sample size. We also compare our customized CNN with other well-known CNNs and shows that our network have a comparable performance with less computational time. We believe that our proposed method can be applied to other limited labelled biological datasets.
http://arxiv.org/abs/1903.06056
Generative Adversarial Network (GAN) which is widely used for Image synthesis via generative modelling suffers peculiarly from training instability. One of the known reasons for this instability is the passage of uninformative gradients from the Discriminator to the Generator due to learning imbalance between them during training. In this work, we propose Multi-Scale Gradients Generative Adversarial Network (MSG-GAN), a simplistic but effective technique for addressing this problem; by allowing the flow of gradients from the Discriminator to the Generator at multiple scales. This results in the Generator acquiring the ability to synthesize synchronized images at multiple resolutions simultaneously. We also highlight a suite of techniques that together buttress the stability of training without excessive hyperparameter tuning. Our MSG-GAN technique is a generic mathematical framework which has multiple instantiations. We present an intuitive form of this technique which uses the concatenation operation in the Discriminator computations and empirically validate it through experiments on the CelebA-HQ, CIFAR10 and Oxford102 flowers datasets and by comparing it with some of the current state-of-the-art techniques.
http://arxiv.org/abs/1903.06048
For assistive robots and virtual agents to achieve ubiquity, machines will need to anticipate the needs of their human counterparts. The field of Learning from Demonstration (LfD) has sought to enable machines to infer predictive models of human behavior for autonomous robot control. However, humans exhibit heterogeneity in decision-making, which traditional LfD approaches fail to capture. To overcome this challenge, we propose a Bayesian LfD framework to infer an integrated representation of all human task demonstrators by inferring human-specific embeddings, thereby distilling their unique characteristics. We validate our approach is able to outperform state-of-the-art techniques on both synthetic and real-world data sets.
http://arxiv.org/abs/1903.06047
Data fusion plays an important role in many technical applications that require efficient processing of multimodal sensory observations. A prominent example is audiovisual signal processing, which has gained increasing attention in automatic speech recognition, speaker localization and related tasks. If appropriately combined with acoustic information, additional visual cues can help to improve the performance in these applications, especially under adverse acoustic conditions. A dynamic weighting of acoustic and visual streams based on instantaneous sensor reliability measures is an efficient approach to data fusion in this context. This paper presents a framework that extends the well-established theory of nonlinear dynamical systems with the notion of dynamic stream weights for an arbitrary number of sensory observations. It comprises a recursive state estimator based on the Gaussian filtering paradigm, which incorporates dynamic stream weights into a framework closely related to the extended Kalman filter. Additionally, a convex optimization approach to estimate oracle dynamic stream weights in fully observed dynamical systems utilizing a Dirichlet prior is presented. This serves as a basis for a generic parameter learning framework of dynamic stream weight estimators. The proposed system is application-independent and can be easily adapted to specific tasks and requirements. A study using audiovisual speaker tracking tasks is considered as an exemplary application in this work. An improved tracking performance of the dynamic stream weight-based estimation framework over state-of-the-art methods is demonstrated in the experiments.
http://arxiv.org/abs/1903.06031
In this work, we propose a fast superpixel-based color transfer method (SCT) between two images. Superpixels enable to decrease the image dimension and to extract a reduced set of color candidates. We propose to use a fast approximate nearest neighbor matching algorithm in which we enforce the match diversity by limiting the selection of the same superpixels. A fusion framework is designed to transfer the matched colors, and we demonstrate the improvement obtained over exact matching results. Finally, we show that SCT is visually competitive compared to state-of-the-art methods.
http://arxiv.org/abs/1903.06010
We consider a novel question answering (QA) task where the machine needs to read from large streaming data (long documents or videos) without knowing when the questions will be given, in which case the existing QA methods fail due to lack of scalability. To tackle this problem, we propose a novel end-to-end reading comprehension method, which we refer to as Episodic Memory Reader (EMR) that sequentially reads the input contexts into an external memory, while replacing memories that are less important for answering unseen questions. Specifically, we train an RL agent to replace a memory entry when the memory is full in order to maximize its QA accuracy at a future timepoint, while encoding the external memory using the transformer architecture to learn representations that considers relative importance between the memory entries. We validate our model on a real-world large-scale textual QA task (TriviaQA) and a video QA task (TVQA), on which it achieves significant improvements over rule-based memory scheduling policies or an RL-based baseline that learns the query-specific importance of each memory independently.
http://arxiv.org/abs/1903.06164
Gaussian process state-space model (GPSSM) is a probabilistic dynamical system that represents unknown transition and/or measurement models as the Gaussian process (GP). The majority of approaches to learning GPSSM are focused on handling given time series data. However, in most dynamical systems, data required for model learning arrives sequentially and accumulates over time. Storing all the data requires large ammounts of memory, and using it for model learning can be computationally infeasible. To overcome this challenge, this paper develops an online inference method for learning the GPSSM (onlineGPSSM) that fuses stochastic variational inference (VI) and online VI. The proposed method can mitigate the computation time issue without catastrophic forgetting and supports adaptation to changes in a system and/or a real environments. Furthermore, we propose a GPSSM-based reinforcement learning (RL) framework for partially observable dynamical systems by combining onlineGPSSM with Bayesian filtering and trajectory optimization algorithms. Numerical examples are presented to demonstrate the applicability of the proposed method.
http://arxiv.org/abs/1903.08643
Harmful algal blooms occur frequently and deteriorate water quality. A reliable method is proposed in this paper to track algal blooms using a set of autonomous surface robots. A satellite image indicates the existence and initial location of the algal bloom for the deployment of the robot system. The algal bloom area is approximated by a circle with time varying location and size. This circle is estimated and circumnavigated by the robots which are able to locally sense its boundary. A multi-agent control algorithm is proposed for the continuous monitoring of the dynamic evolution of the algal bloom. Such algorithm comprises of a decentralized least squares estimation of the target and a controller for circumnavigation. We prove the convergence of the robots to the circle and in equally spaced positions around it. Simulation results with data provided by the SINMOD ocean model are used to illustrate the theoretical results.
http://arxiv.org/abs/1903.05993
While most previous work has focused on different pretraining objectives and architectures for transfer learning, we ask how to best adapt the pretrained model to a given target task. We focus on the two most common forms of adaptation, feature extraction (where the pretrained weights are frozen), and directly fine-tuning the pretrained model. Our empirical results across diverse NLP tasks with two state-of-the-art models show that the relative performance of fine-tuning vs. feature extraction depends on the similarity of the pretraining and target tasks. We explore possible explanations for this finding and provide a set of adaptation guidelines for the NLP practitioner.
http://arxiv.org/abs/1903.05987
Estimating the 6D pose of objects from images is an important problem in various applications such as robot manipulation and virtual reality. While direct regression of images to object poses has limited accuracy, matching rendered images of an object against the observed image can produce accurate results. In this work, we propose a novel deep neural network for 6D pose matching named DeepIM. Given an initial pose estimation, our network is able to iteratively refine the pose by matching the rendered image against the observed image. The network is trained to predict a relative pose transformation using an untangled representation of 3D location and 3D orientation and an iterative training process. Experiments on two commonly used benchmarks for 6D pose estimation demonstrate that DeepIM achieves large improvements over state-of-the-art methods. We furthermore show that DeepIM is able to match previously unseen objects.
http://arxiv.org/abs/1804.00175
A central problem in hyperspectral image classification is obtaining high classification accuracy when using a limited amount of labelled data. In this paper we present a novel graph-based framework, which aims to tackle this problem in the presence of large scale data input. Our approach utilises a novel superpixel method, specifically designed for hyperspectral data, to define meaningful local regions in an image, which with high probability share the same classification label. We then extract spectral and spatial features from these regions and use these to produce a contracted weighted graph-representation, where each node represents a region rather than a pixel. Our graph is then fed into a graph-based semi-supervised classifier which gives the final classification. We show that using superpixels in a graph representation is an effective tool for speeding up graphical classifiers applied to hyperspectral images. We demonstrate through exhaustive quantitative and qualitative results that our proposed method produces accurate classifications when an incredibly small amount of labelled data is used. We show that our approach mitigates the major drawbacks of existing approaches, resulting in our approach outperforming several comparative state-of-the-art techniques.
http://arxiv.org/abs/1903.06548
Constructing the adjacency graph is fundamental to graph-based clustering. Graph learning in kernel space has shown impressive performance on a number of benchmark data sets. However, its performance is largely determined by the chosen kernel matrix. To address this issue, the previous multiple kernel learning algorithm has been applied to learn an optimal kernel from a group of predefined kernels. This approach might be sensitive to noise and limits the representation ability of the consensus kernel. In contrast to existing methods, we propose to learn a low-rank kernel matrix which exploits the similarity nature of the kernel matrix and seeks an optimal kernel from the neighborhood of candidate kernels. By formulating graph construction and kernel learning in a unified framework, the graph and consensus kernel can be iteratively enhanced by each other. Extensive experimental results validate the efficacy of the proposed method.
http://arxiv.org/abs/1903.05962