Like many computer vision problems, human pose estimation is a challenging problem in that recognizing a body part requires not only information from local area but also from areas with large spatial distance. In order to spatially pass information, large convolutional kernels and deep layers have been normally used, introducing high computation cost and large parameter space. Luckily for pose estimation, human body is geometrically structured in images, enabling modeling of spatial dependency. In this paper, we propose a spatial shortcut network for pose estimation task, where information is easier to flow spatially. We evaluate our model with detailed analyses and present its outstanding performance with smaller structure.
https://arxiv.org/abs/1904.03141
Models trained in the context of continual learning (CL) should be able to learn from a stream of data over an undefined period of time. The main challenges herein are: 1) maintaining old knowledge while simultaneously benefiting from it when learning new tasks, and 2) guaranteeing model scalability with a growing amount of data to learn from. In order to tackle these challenges, we introduce Dynamic Generative Memory (DGM) - a synaptic plasticity driven framework for continual learning. DGM relies on conditional generative adversarial networks with learnable connection plasticity realized with neural masking. Specifically, we evaluate two variants of neural masking: applied to (i) layer activations and (ii) to connection weights directly. Furthermore, we propose a dynamic network expansion mechanism that ensures sufficient model capacity to accommodate for continually incoming tasks. The amount of added capacity is determined dynamically from the learned binary mask. We evaluate DGM in the continual class-incremental setup on visual classification tasks.
https://arxiv.org/abs/1904.03137
In this paper, we present RT-GCC-NMF: a real-time (RT), two-channel blind speech enhancement algorithm that combines the non-negative matrix factorization (NMF) dictionary learning algorithm with the generalized cross-correlation (GCC) spatial localization method. Using a pre-learned universal NMF dictionary, RT-GCC-NMF operates in a frame-by-frame fashion by associating individual dictionary atoms to target speech or background interference based on their estimated time-delay of arrivals (TDOA). We evaluate RT-GCC-NMF on two-channel mixtures of speech and real-world noise from the Signal Separation and Evaluation Campaign (SiSEC). We demonstrate that this approach generalizes to new speakers, acoustic environments, and recording setups from very little training data, and outperforms all but one of the algorithms from the SiSEC challenge in terms of overall Perceptual Evaluation methods for Audio Source Separation (PEASS) scores and compares favourably to the ideal binary mask baseline. Over a wide range of input SNRs, we show that this approach simultaneously improves the PEASS and signal to noise ratio (SNR)-based Blind Source Separation (BSS) Eval objective quality metrics as well as the short-time objective intelligibility (STOI) and extended STOI (ESTOI) objective speech intelligibility metrics. A flexible, soft masking function in the space of NMF activation coefficients offers real-time control of the trade-off between interference suppression and target speaker fidelity. Finally, we use an asymmetric short-time Fourier transform (STFT) to reduce the inherent algorithmic latency of RT-GCC-NMF from 64 ms to 2 ms with no loss in performance. We demonstrate that latencies within the tolerable range for hearing aids are possible on current hardware platforms.
https://arxiv.org/abs/1904.03130
In this paper, we propose a novel interpretation method tailored to histological Whole Slide Image (WSI) processing. A Deep Neural Network (DNN), inspired by Bag-of-Features models is equipped with a Multiple Instance Learning (MIL) branch and trained with weak supervision for WSI classification. MIL avoids label ambiguity and enhances our model’s expressive power without guiding its attention. We utilize a fine-grained logit heatmap of the models activations to interpret its decision-making process. The proposed method is quantitatively and qualitatively evaluated on two challenging histology datasets, outperforming a variety of baselines. In addition, two expert pathologists were consulted regarding the interpretability provided by our method and acknowledged its potential for integration into several clinical applications.
https://arxiv.org/abs/1904.03127
We present an approach to leaf level segmentation of images of Arabidopsis thaliana plants based upon detected edges. We introduce a novel approach to edge classification, which forms an important part of a method to both count the leaves and establish the leaf area of a growing plant from images obtained in a high-throughput phenotyping system. Our technique uses a relatively shallow convolutional neural network to classify image edges as background, plant edge, leaf-on-leaf edge or internal leaf noise. The edges themselves were found using the Canny edge detector and the classified edges can be used with simple image processing techniques to generate a region-based segmentation in which the leaves are distinct. This approach is strong at distinguishing occluding pairs of leaves where one leaf is largely hidden, a situation which has proved troublesome for plant image analysis systems in the past. In addition, we introduce the publicly available plant image dataset that was used for this work.
https://arxiv.org/abs/1904.03124
In a corpus of data, outliers are either errors: mistakes in the data that are counterproductive, or are unique: informative samples that improve model robustness. Identifying outliers can lead to better datasets by (1) removing noise in datasets and (2) guiding collection of additional data to fill gaps. However, the problem of detecting both outlier types has received relatively little attention in NLP, particularly for dialog systems. We introduce a simple and effective technique for detecting both erroneous and unique samples in a corpus of short texts using neural sentence embeddings combined with distance-based outlier detection. We also present a novel data collection pipeline built atop our detection technique to automatically and iteratively mine unique data samples while discarding erroneous samples. Experiments show that our outlier detection technique is effective at finding errors while our data collection pipeline yields highly diverse corpora that in turn produce more robust intent classification and slot-filling models.
https://arxiv.org/abs/1904.03122
Action segmentation is the task of predicting the actions in each frame of a video. Because of the high cost of preparing training videos with full supervision for action segmentation, weakly supervised approaches which are able to learn only from transcripts are very appealing. In this paper, we propose a new approach for weakly supervised action segmentation based on a two branch network. The two branches of our network predict two redundant but different representations for action segmentation. During training we introduce a new mutual consistency loss (MuCon) that enforces that these two representations are consistent. Using MuCon and a transcript prediction loss, our network achieves state-of-the-art results for action segmentation and action alignment while being fully differentiable and faster to train since it does not require a costly alignment step during training.
https://arxiv.org/abs/1904.03116
The EMNLP 2018 workshop BlackboxNLP was dedicated to resources and techniques specifically developed for analyzing and understanding the inner-workings and representations acquired by neural models of language. Approaches included: systematic manipulation of input to neural networks and investigating the impact on their performance, testing whether interpretable knowledge can be decoded from intermediate representations acquired by neural networks, proposing modifications to neural network architectures to make their knowledge state or generated output more explainable, and examining the performance of networks on simplified or formal languages. Here we review a number of representative studies in each category.
http://arxiv.org/abs/1904.04063
We introduce entity post-modifier generation as an instance of a collaborative writing task. Given a sentence about a target entity, the task is to automatically generate a post-modifier phrase that provides contextually relevant information about the entity. For example, for the sentence, “Barack Obama, ___, supported the #MeToo movement.”, the phrase “a father of two girls” is a contextually relevant post-modifier. To this end, we build PoMo, a post-modifier dataset created automatically from news articles reflecting a journalistic need for incorporating entity information that is relevant to a particular news event. PoMo consists of more than 231K sentences with post-modifiers and associated facts extracted from Wikidata for around 57K unique entities. We use crowdsourcing to show that modeling contextual relevance is necessary for accurate post-modifier generation. We adapt a number of existing generation approaches as baselines for this dataset. Our results show there is large room for improvement in terms of both identifying relevant facts to include (knowing which claims are relevant gives a >20% improvement in BLEU score), and generating appropriate post-modifier text for the context (providing relevant claims is not sufficient for accurate generation). We conduct an error analysis that suggests promising directions for future research.
https://arxiv.org/abs/1904.03111
Model architectures have been dramatically increasing in size, improving performance at the cost of resource requirements. In this paper we propose 3DQ, a ternary quantization method, applied for the first time to 3D Fully Convolutional Neural Networks (F-CNNs), enabling 16x model compression while maintaining performance on par with full precision models. We extensively evaluate 3DQ on two datasets for the challenging task of whole brain segmentation. Additionally, we showcase our method’s ability to generalize on two common 3D architectures, namely 3D U-Net and V-Net. Outperforming a variety of baselines, the proposed method is capable of compressing large 3D models to a few MBytes, alleviating the storage needs in space critical applications.
https://arxiv.org/abs/1904.03110
Self-attention networks (SANs) have drawn increasing interest due to their high parallelization in computation and flexibility in modeling dependencies. SANs can be further enhanced with multi-head attention by allowing the model to attend to information from different representation subspaces. In this work, we propose novel convolutional self-attention networks, which offer SANs the abilities to 1) strengthen dependencies among neighboring elements, and 2) model the interaction between features extracted by multiple attention heads. Experimental results of machine translation on different language pairs and model settings show that our approach outperforms both the strong Transformer baseline and other existing models on enhancing the locality of SANs. Comparing with prior studies, the proposed model is parameter free in terms of introducing no more parameters.
https://arxiv.org/abs/1904.03107
Developers are usually unaware of the impact of code changes to the performance of software systems. Although developers can analyze the performance of a system by executing, for instance, a performance test to compare the performance of two consecutive versions of the system, changing from a programming task to a testing task would disrupt the development flow. In this paper, we propose the use of a city visualization that dynamically provides developers with a pervasive view of the continuous performance of a system. We use an immersive augmented reality device (Microsoft HoloLens) to display our visualization and extend the integrated development environment on a computer screen to use the physical space. We report on technical details of the design and implementation of our visualization tool, and discuss early feedback that we collected of its usability. Our investigation explores a new visual metaphor to support the exploration and analysis of possibly very large and multidimensional performance data. Our initial result indicates that the city metaphor can be adequate to analyze dynamic performance data on a large and non-trivial software system.
http://arxiv.org/abs/1904.06399
Multi-head attention is appealing for its ability to jointly extract different types of information from multiple representation subspaces. Concerning the information aggregation, a common practice is to use a concatenation followed by a linear transformation, which may not fully exploit the expressiveness of multi-head attention. In this work, we propose to improve the information aggregation for multi-head attention with a more powerful routing-by-agreement algorithm. Specifically, the routing algorithm iteratively updates the proportion of how much a part (i.e. the distinct information learned from a specific subspace) should be assigned to a whole (i.e. the final output representation), based on the agreement between parts and wholes. Experimental results on linguistic probing tasks and machine translation tasks prove the superiority of the advanced information aggregation over the standard linear transformation.
https://arxiv.org/abs/1904.03100
Recently, the Transformer model that is based solely on attention mechanisms, has advanced the state-of-the-art on various machine translation tasks. However, recent studies reveal that the lack of recurrence hinders its further improvement of translation capacity. In response to this problem, we propose to directly model recurrence for Transformer with an additional recurrence encoder. In addition to the standard recurrent neural network, we introduce a novel attentive recurrent network to leverage the strengths of both attention and recurrent networks. Experimental results on the widely-used WMT14 English-German and WMT17 Chinese-English translation tasks demonstrate the effectiveness of the proposed approach. Our studies also reveal that the proposed model benefits from a short-cut that bridges the source and target sequences with a single recurrent layer, which outperforms its deep counterpart.
https://arxiv.org/abs/1904.03092
Tomography medical imaging is essential in the clinical workflow of modern cancer radiotherapy. Radiation oncologists identify cancerous tissues, applying delineation on treatment regions throughout all image slices. This kind of task is often formulated as a volumetric segmentation task by means of 3D convolutional networks with considerable computational cost. Instead, inspired by the treating methodology of considering meaningful information across slices, we used Gated Graph Neural Network to frame this problem more efficiently. More specifically, we propose convolutional recurrent Gated Graph Propagator (GGP) to propagate high-level information through image slices, with learnable adjacency weighted matrix. Furthermore, as physicians often investigate a few specific slices to refine their decision, we model this slice-wise interaction procedure to further improve our segmentation result. This can be set by editing any slice effortlessly as updating predictions of other slices using GGP. To evaluate our method, we collect an Esophageal Cancer Radiotherapy Target Treatment Contouring dataset of 81 patients which includes tomography images with radiotherapy target. On this dataset, our convolutional graph network produces state-of-the-art results and outperforms the baselines. With the addition of interactive setting, performance is improved even further. Our method has the potential to be easily applied to diverse kinds of medical tasks with volumetric images. Incorporating both the ability to make a feasible prediction and to consider the human interactive input, the proposed method is suitable for clinical scenarios.
https://arxiv.org/abs/1904.03086
This paper describes our submission to SemEval-2019 Task 7: RumourEval: Determining Rumor Veracity and Support for Rumors. We participated in both subtasks. The goal of subtask A is to classify the type of interaction between a rumorous social media post and a reply post as support, query, deny, or comment. The goal of subtask B is to predict the veracity of a given rumor. For subtask A, we implement a CNN-based neural architecture using ELMo embeddings of post text combined with auxiliary features and achieve a F1-score of 44.6%. For subtask B, we employ a MLP neural network leveraging our estimates for subtask A and achieve a F1-score of 30.1% (second place in the competition). We provide results and analysis of our system performance and present ablation experiments.
https://arxiv.org/abs/1904.03084
Diffusion magnetic resonance imaging (diffusion MRI) is a non-invasive microstructure assessment method. Scalar measures quantifying micro-structural tissue properties can be obtained using diffusion models and data processing pipelines. However, it is costly and time consuming to collect high quality diffusion data. We demonstrate how Generative Adversarial Networks (GANs) can be used to generate diffusion scalar measures from structural MR images in a single optimized step, without diffusion models and diffusion data. We show that the used Cycle-GAN model can synthesize visually realistic and quantitatively accurate diffusion-derived scalar measures.
http://arxiv.org/abs/1810.02683
The last decade has shown a tremendous success in solving various computer vision problems with the help of deep learning techniques. Lately, many works have demonstrated that learning-based approaches with suitable network architectures even exhibit superior performance for the solution of (ill-posed) image reconstruction problems such as deblurring, super-resolution, or medical image reconstruction. The drawback of purely learning-based methods, however, is that they cannot provide provable guarantees for the trained network to follow a given data formation process during inference. In this work we propose energy dissipating networks that iteratively compute a descent direction with respect to a given cost function or energy at the currently estimated reconstruction. Therefore, an adaptive step size rule such as a line-search, along with a suitable number of iterations can guarantee the reconstruction to follow a given data formation model encoded in the energy to arbitrary precision, and hence control the model’s behavior even during test time. We prove that under standard assumptions, descent using the direction predicted by the network converges (linearly) to the global minimum of the energy. We illustrate the effectiveness of the proposed approach in experiments on single image super resolution and computed tomography (CT) reconstruction, and further illustrate extensions to convex feasibility problems.
https://arxiv.org/abs/1904.03081
Adversarial training has been highly successful for single-image super-resolution, as it yields realistic and highly detailed results. Despite this success, current state-of-the-art methods for video super-resolution still favor simpler norms such as $L_2$ over adversarial loss functions. The averaging nature of direct vector norms as loss functions easily leads to temporal smoothness and coherence caused by an undesirable lack of spatial detail in the generated images. In our work, we instead propose an adversarial training for video super-resolution that leads to temporally coherent solutions without sacrificing spatial detail. Our work focuses on novel loss formulations for video super-resolution, the power of which we demonstrate based on an established generator framework. We show that temporal adversarial learning is the key to achieving photo-realistic and temporally coherent detail. Besides the spatio-temporal discriminator, we propose a novel Ping-Pong loss that can effectively remove temporal artifacts in recurrent networks without reducing perceptual quality. Quantifying the temporal coherence for video super-resolution tasks has also not been addressed previously. We propose a first set of metrics to evaluate the accuracy as well as the perceptual quality of the temporal evolution. A series of user studies also confirm the ranking achieved via these metrics. Overall, our method outperforms previous work by yielding more detailed images with natural temporal changes.
https://arxiv.org/abs/1811.09393
Dense pixel matching is important for many computer vision tasks such as disparity and flow estimation. We present a robust, unified descriptor network that considers a large context region with high spatial variance. Our network has a very large receptive field and avoids striding layers to maintain spatial resolution. These properties are achieved by creating a novel neural network layer that consists of multiple, parallel, stacked dilated convolutions (SDC). Several of these layers are combined to form our SDC descriptor network. In our experiments, we show that our SDC features outperform state-of-the-art feature descriptors in terms of accuracy and robustness. In addition, we demonstrate the superior performance of SDC in state-of-the-art stereo matching, optical flow and scene flow algorithms on several famous public benchmarks.
https://arxiv.org/abs/1904.03076
Lesion segmentation from the surrounding skin is the first task for developing automatic Computer-Aided Diagnosis of skin cancer. Variant features of lesion like uneven distribution of color, irregular shape, border and texture make this task challenging. The contribution of this paper is to present and compare two different approaches to skin lesion segmentation. The first approach uses watershed, while the second approach uses mean-shift. Pre-processing steps were performed in both approaches for removing hair and dark borders of microscopic images. The Evaluation of the proposed approaches was performed using Jaccard Index (Intersection over Union or IoU). An additional contribution of this paper is to present pipelines for performing pre-processing and segmentation applying existing segmentation and morphological algorithms which led to promising results. On average, the first approach showed better performance than the second one with average Jaccard Index over 200 ISIC-2017 challenge images are 89.16% and 76.94% respectively.
https://arxiv.org/abs/1904.03075
In this paper we propose a method of single-channel speaker-independent multi-speaker speech separation for an unknown number of speakers. As opposed to previous works, in which the number of speakers is assumed to be known in advance and speech separation models are specific for the number of speakers, our proposed method can be applied to cases with different numbers of speakers using a single model by recursively separating a speaker. To make the separation model recursively applicable, we propose one-and-rest permutation invariant training (OR-PIT). Evaluation on WSJ0-2mix and WSJ0-3mix datasets show that our proposed method achieves state-of-the-art results for two- and three-speaker mixtures with a single model. Moreover, the same model can separate four-speaker mixture, which was never seen during the training. We further propose the detection of the number of speakers in a mixture during recursive separation and show that this approach can more accurately estimate the number of speakers than detection in advance by using a deep neural network based classifier.
https://arxiv.org/abs/1904.03065
In this work, we present an algorithm for robot replacement to increase the operational time of a multi-robot payload transport system. Our system comprises a group of nonholonomic wheeled mobile robots traversing on a known trajectory. We design a multi-robot system with loosely coupled robots that ensures the system lasts much longer than the battery life of an individual robot. A system level optimization is presented, to decide on the operational state (charging or discharging) of each robot in the system. The charging state implies that the robot is not in a formation and is kept on charge whereas the discharging state implies that the robot is a part of the formation. Robot battery recharge hubs are present along the trajectory. Robots in the formation can be replaced at these hub locations with charged robots using a replacement mechanism. We showcase the efficacy of the proposed scheduling framework through simulations and experiments with real robots.
http://arxiv.org/abs/1904.03049
Legged robots, specifically quadrupeds, are becoming increasingly attractive for industrial applications such as inspection. However, to leave the laboratory and to become useful to an end user requires reliability in harsh conditions. From the perspective of perception, it is essential to be able to accurately estimate the robot’s state despite challenges such as uneven or slippery terrain, textureless and reflective scenes, as well as dynamic camera occlusions. We are motivated to reduce the dependency on foot contact classifications, which fail when slipping, and to reduce position drift during dynamic motions such as trotting. To this end, we present a factor graph optimization method for state estimation which tightly fuses and smooths inertial navigation, leg odometry and visual odometry. The effectiveness of the approach is demonstrated using the ANYmal quadruped robot navigating in a realistic outdoor industrial environment. This experiment included trotting, walking, crossing obstacles and ascending a staircase. The proposed approach decreased the relative position error by up to 55% and absolute position error by 76% compared to kinematic-inertial odometry.
http://arxiv.org/abs/1904.03048
The detection of new or enlarged white-matter lesions in multiple sclerosis is a vital task in the monitoring of patients undergoing disease-modifying treatment for multiple sclerosis. However, the definition of ‘new or enlarged’ is not fixed, and it is known that lesion-counting is highly subjective, with high degree of inter- and intra-rater variability. Automated methods for lesion quantification hold the potential to make the detection of new and enlarged lesions consistent and repeatable. However, the majority of lesion segmentation algorithms are not evaluated for their ability to separate progressive from stable patients, despite this being a pressing clinical use-case. In this paper we show that change in volumetric measurements of lesion load alone is not a good method for performing this separation, even for highly performing segmentation methods. Instead, we propose a method for identifying lesion changes of high certainty, and establish on a dataset of longitudinal multiple sclerosis cases that this method is able to separate progressive from stable timepoints with a very high level of discrimination (AUC = 0.99), while changes in lesion volume are much less able to perform this separation (AUC = 0.71). Validation of the method on a second external dataset confirms that the method is able to generalize beyond the setting in which it was trained, achieving an accuracy of 83% in separating stable and progressive timepoints. Both lesion volume and count have previously been shown to be strong predictors of disease course across a population. However, we demonstrate that for individual patients, changes in these measures are not an adequate means of establishing no evidence of disease activity. Meanwhile, directly detecting tissue which changes, with high confidence, from non-lesion to lesion is a feasible methodology for identifying radiologically active patients.
https://arxiv.org/abs/1904.03041
Large sense-annotated datasets are increasingly necessary for training deep supervised systems in word sense disambiguation. However, gathering high-quality sense-annotated data for as many instances as possible is a laborious and expensive task. This has led to the proliferation of automatic and semi-automatic methods for overcoming the so-called knowledge-acquisition bottleneck. In this short survey we present an overview of currently available sense-annotated corpora, both manually and (semi)automatically constructed, for diverse languages and lexical resources (i.e. WordNet, Wikipedia, BabelNet). General statistics and specific features of each sense-annotated dataset are also provided.
http://arxiv.org/abs/1802.04744
Many text corpora exhibit socially problematic biases, which can be propagated or amplified in the models trained on such data. For example, doctor cooccurs more frequently with male pronouns than female pronouns. In this study we (i) propose a metric to measure gender bias; (ii) measure bias in a text corpus and the text generated from a recurrent neural network language model trained on the text corpus; (iii) propose a regularization loss term for the language model that minimizes the projection of encoder-trained embeddings onto an embedding subspace that encodes gender; (iv) finally, evaluate efficacy of our proposed method on reducing gender bias. We find this regularization method to be effective in reducing gender bias up to an optimal weight assigned to the loss term, beyond which the model becomes unstable as the perplexity increases. We replicate this study on three training corpora—Penn Treebank, WikiText-2, and CNN/Daily Mail—resulting in similar conclusions.
https://arxiv.org/abs/1904.03035
In this paper, the current state of security in robotics is described to be in need of review. When we consider safety mechanisms implemented in an Internet-connected robot, the requirement of safety becomes a crucial security requirement. Upon review of the current state of security in the field of robotics, four key requirements are in need of addressing: the supply chain for calibration, integrity and authenticity of commands (i.e. in teleoperation), physical-plane security and finally, secure, controlled logging and auditing.
http://arxiv.org/abs/1904.03033
Multimedia applications often require concurrent solutions to multiple tasks. These tasks hold clues to each-others solutions, however as these relations can be complex this remains a rarely utilized property. When task relations are explicitly defined based on domain knowledge multi-task learning (MTL) offers such concurrent solutions, while exploiting relatedness between multiple tasks performed over the same dataset. In most cases however, this relatedness is not explicitly defined and the domain expert knowledge that defines it is not available. To address this issue, we introduce Selective Sharing, a method that learns the inter-task relatedness from secondary latent features while the model trains. Using this insight, we can automatically group tasks and allow them to share knowledge in a mutually beneficial way. We support our method with experiments on 5 datasets in classification, regression, and ranking tasks and compare to strong baselines and state-of-the-art approaches showing a consistent improvement in terms of accuracy and parameter counts. In addition, we perform an activation region analysis showing how Selective Sharing affects the learned representation.
https://arxiv.org/abs/1904.03011
Planning in stochastic and partially observable environments is a central issue in artificial intelligence. One commonly used technique for solving such a problem is by constructing an accurate model firstly. Although some recent approaches have been proposed for learning optimal behaviour under model uncertainty, prior knowledge about the environment is still needed to guarantee the performance of the proposed algorithms. With the benefits of the Predictive State Representations~(PSRs) approach for state representation and model prediction, in this paper, we introduce an approach for planning from scratch, where an offline PSR model is firstly learned and then combined with online Monte-Carlo tree search for planning with model uncertainty. By comparing with the state-of-the-art approach of planning with model uncertainty, we demonstrated the effectiveness of the proposed approaches along with the proof of their convergence. The effectiveness and scalability of our proposed approach are also tested on the RockSample problem, which are infeasible for the state-of-the-art BA-POMDP based approaches.
https://arxiv.org/abs/1904.03008
Despite there being clear evidence for top-down (e.g., attentional) effects in biological spatial hearing, relatively few machine hearing systems exploit top-down model-based knowledge in sound localisation. This paper addresses this issue by proposing a novel framework for binaural sound localisation that combines model-based information about the spectral characteristics of sound sources and deep neural networks (DNNs). A target source model and a background source model are first estimated during a training phase using spectral features extracted from sound signals in isolation. When the identity of the background source is not available, a universal background model can be used. During testing, the source models are used jointly to explain the mixed observations and improve the localisation process by selectively weighting source azimuth posteriors output by a DNN-based localisation system. To address the possible mismatch between training and testing, a model adaptation process is further employed on-the-fly during testing, which adapts the background model parameters directly from the noisy observations in an iterative manner. The proposed system therefore combines model-based and data-driven information flow within a single computational framework. The evaluation task involved localisation of a target speech source in the presence of an interfering source and room reverberation. Our experiments show that by exploiting model-based information in this way, sound localisation performance can be improved substantially under various noisy and reverberant conditions.
https://arxiv.org/abs/1904.03006
This paper presents a novel machine-hearing system that exploits deep neural networks (DNNs) and head movements for robust binaural localisation of multiple sources in reverberant environments. DNNs are used to learn the relationship between the source azimuth and binaural cues, consisting of the complete cross-correlation function (CCF) and interaural level differences (ILDs). In contrast to many previous binaural hearing systems, the proposed approach is not restricted to localisation of sound sources in the frontal hemifield. Due to the similarity of binaural cues in the frontal and rear hemifields, front-back confusions often occur. To address this, a head movement strategy is incorporated in the localisation model to help reduce the front-back errors. The proposed DNN system is compared to a Gaussian mixture model (GMM) based system that employs interaural time differences (ITDs) and ILDs as localisation features. Our experiments show that the DNN is able to exploit information in the CCF that is not available in the ITD cue, which together with head movements substantially improves localisation accuracies under challenging acoustic scenarios in which multiple talkers and room reverberation are present.
https://arxiv.org/abs/1904.03001
When humans have to solve everyday tasks, they simply pick the objects that are most suitable. While the question which object should one use for a specific task sounds trivial for humans, it is very difficult to answer for robots or other autonomous systems. This issue, however, is not addressed by current benchmarks for object detection that focus on detecting object categories. We therefore introduce the COCO-Tasks dataset which comprises about 40,000 images where the most suitable objects for 14 tasks have been annotated. We furthermore propose an approach that detects the most suitable objects for a given task. The approach builds on a Gated Graph Neural Network to exploit the appearance of each object as well as the global context of all present objects in the scene. In our experiments, we show that the proposed approach outperforms other approaches that are evaluated on the dataset like classification or ranking approaches.
http://arxiv.org/abs/1904.03000
Attention mechanism aims to increase the representation power by focusing on important features and suppressing unnecessary ones. For convolutional neural networks (CNNs), attention is typically learned with local convolutions, which ignores the global information and the hidden relation. How to efficiently exploit the long-range context to globally learn attention is underexplored. In this paper, we propose an effective Relation-Aware Global Attention (RGA) module for CNNs to fully exploit the global correlations to infer the attention. Specifically, when computing the attention at a feature position, in order to grasp information of global scope, we propose to stack the relations, i.e., its pairwise correlations/affinities with all the feature positions, and the feature itself together for learning the attention with convolutional operations. Given an intermediate feature map, we have validated the effectiveness of this design across both the spatial and channel dimensions. When applied to the task of person re-identification, our model achieves the state-of-the-art performance. Extensive ablation studies demonstrate that our RGA can significantly enhance the feature representation power. We further demonstrate the general applicability of RGA to vision tasks by applying it to the scene segmentation and image classification tasks resulting in consistent performance improvement.
https://arxiv.org/abs/1904.02998
We present a novel method for mapping unrestricted text to knowledge graph entities by framing the task as a sequence-to-sequence problem. Specifically, given the encoded state of an input text, our decoder directly predicts paths in the knowledge graph, starting from the root and ending at the target node following hypernym-hyponym relationships. In this way, and in contrast to other text-to-entity mapping systems, our model outputs hierarchically structured predictions that are fully interpretable in the context of the underlying ontology, in an end-to-end manner. We present a proof-of-concept experiment with encouraging results, comparable to those of state-of-the-art systems.
https://arxiv.org/abs/1904.02996
Cooperative vehicle platooning applications increasingly demand realistic simulation tools to ease their validation and to bridge the gap between development and real-world deployment. However, their complexity and cost often hinder its validation in the real world. In this paper, we propose a realistic simulation framework for vehicular platoons that integrates Gazebo with OMNeT++ over Robot Operating System (ROS) to support the simulation of realistic scenarios of autonomous vehicular platoons and their cooperative control.
http://arxiv.org/abs/1904.02994
Sleep-disordered breathing (SDB) is a serious and prevalent condition, and acoustic analysis via consumer devices (e.g. smartphones) offers a low-cost solution to screening for it. We present a novel approach for the acoustic identification of SDB sounds, such as snoring, using bottleneck features learned from a corpus of whole-night sound recordings. Two types of bottleneck features are described, obtained by applying a deep autoencoder to the output of an auditory model or a short-term autocorrelation analysis. We investigate two architectures for snore sound detection: a tandem system and a hybrid system. In both cases, a `language model’ (LM) was incorporated to exploit information about the sequence of different SDB events. Our results show that the proposed bottleneck features give better performance than conventional mel-frequency cepstral coefficients, and that the tandem system outperforms the hybrid system given the limited amount of labelled training data available. The LM made a small improvement to the performance of both classifiers.
https://arxiv.org/abs/1904.02992
In this paper, we present neural model architecture submitted to the SemEval-2019 Task 9 competition: “Suggestion Mining from Online Reviews and Forums”. We participated in both subtasks for domain specific and also cross-domain suggestion mining. We proposed a recurrent neural network architecture that employs Bi-LSTM layers and also self-attention mechanism. Our architecture tries to encode words via word representations using ELMo and ensembles multiple models to achieve better results. We performed experiments with different setups of our proposed model involving weighting of prediction classes for loss function. Our best model achieved in official test evaluation score of 0.6816 for subtask A and 0.6850 for subtask B. In official results, we achieved 12th and 10th place in subtasks A and B, respectively.
https://arxiv.org/abs/1904.02981
We present semantic attribute matching networks (SAM-Net) for jointly establishing correspondences and transferring attributes across semantically similar images, which intelligently weaves the advantages of the two tasks while overcoming their limitations. SAM-Net accomplishes this through an iterative process of establishing reliable correspondences by reducing the attribute discrepancy between the images and synthesizing attribute transferred images using the learned correspondences. To learn the networks using weak supervisions in the form of image pairs, we present a semantic attribute matching loss based on the matching similarity between an attribute transferred source feature and a warped target feature. With SAM-Net, the state-of-the-art performance is attained on several benchmarks for semantic matching and attribute transfer.
https://arxiv.org/abs/1904.02969
Real world applications of stereo depth estimation require models that are robust to dynamic variations in the environment. Even though deep learning based stereo methods are successful, they often fail to generalize to unseen variations in the environment, making them less suitable for practical applications such as autonomous driving. In this work, we introduce a “learning-to-adapt” framework that enables deep stereo methods to continuously adapt to new target domains in an unsupervised manner. Specifically, our approach incorporates the adaptation procedure into the learning objective to obtain a base set of parameters that are better suited for unsupervised online adaptation. To further improve the quality of the adaptation, we learn a confidence measure that effectively masks the errors introduced during the unsupervised adaptation. We evaluate our method on synthetic and real-world stereo datasets and our experiments evidence that learning-to-adapt is, indeed beneficial for online adaptation on vastly different domains.
https://arxiv.org/abs/1904.02957
ELMo embeddings (Peters et. al, 2018) had a huge impact on the NLP community and may recent publications use these embeddings to boost the performance for downstream NLP tasks. However, integration of ELMo embeddings in existent NLP architectures is not straightforward. In contrast to traditional word embeddings, like GloVe or word2vec embeddings, the bi-directional language model of ELMo produces three 1024 dimensional vectors per token in a sentence. Peters et al. proposed to learn a task-specific weighting of these three vectors for downstream tasks. However, this proposed weighting scheme is not feasible for certain tasks, and, as we will show, it does not necessarily yield optimal performance. We evaluate different methods that combine the three vectors from the language model in order to achieve the best possible performance in downstream NLP tasks. We notice that the third layer of the published language model often decreases the performance. By learning a weighted average of only the first two layers, we are able to improve the performance for many datasets. Due to the reduced complexity of the language model, we have a training speed-up of 19-44% for the downstream task.
https://arxiv.org/abs/1904.02954
Object detection generally requires sliding-window classifiers in tradition or anchor-based predictions in modern deep learning approaches. However, either of these approaches requires tedious configurations in windows or anchors. In this paper, taking pedestrian detection as an example, we provide a new perspective where detecting objects is motivated as a high-level semantic feature detection task. Like edges, corners, blobs and other feature detectors, the proposed detector scans for feature points all over the image, for which the convolution is naturally suited. However, unlike these traditional low-level features, the proposed detector goes for a higher-level abstraction, that is, we are looking for central points where there are pedestrians, and modern deep models are already capable of such a high-level semantic abstraction. Besides, like blob detection, we also predict the scales of the pedestrian points, which is also a straightforward convolution. Therefore, in this paper, pedestrian detection is simplified as a straightforward center and scale prediction task through convolutions. This way, the proposed method enjoys an anchor-free setting. Though structurally simple, it presents competitive accuracy and good speed on challenging pedestrian detection benchmarks, and hence leading to a new attractive pedestrian detector. Code and models will be available at \url{this https URL}.
https://arxiv.org/abs/1904.02948
Outdoor visual localization is a crucial component to many computer vision systems. We propose an approach to localization from images that is designed to explicitly handle the strong variations in appearance happening between daytime and nighttime. As revealed by recent long-term localization benchmarks, both traditional feature-based and retrieval-based approaches still struggle to handle such changes. Our novel localization method combines a state-of-the-art image retrieval architecture with condition-specific sub-networks allowing the computation of global image descriptors that are explicitly dependent of the capturing conditions. We show that our approach improves localization by a factor of almost 300\% compared to the popular VLAD-based methods on nighttime localization.
http://arxiv.org/abs/1812.03707
This study explores the necessity of performing cross-corpora evaluation for grammatical error correction (GEC) models. GEC models have been previously evaluated based on a single commonly applied corpus: the CoNLL-2014 benchmark. However, the evaluation remains incomplete because the task difficulty varies depending on the test corpus and conditions such as the proficiency levels of the writers and essay topics. To overcome this limitation, we evaluate the performance of several GEC models, including NMT-based (LSTM, CNN, and transformer) and an SMT-based model, against various learner corpora (CoNLL-2013, CoNLL-2014, FCE, JFLEG, ICNALE, and KJ). Evaluation results reveal that the models’ rankings considerably vary depending on the corpus, indicating that single-corpus evaluation is insufficient for GEC models.
https://arxiv.org/abs/1904.02927
In the context of deep learning, neural networks with multiple branches have been used that each solve different tasks. Such ramified networks typically start with a number of shared layers, after which different tasks branch out into their own sequence of layers. As the number of possible network configurations is combinatorially large, prior work has often relied on ad hoc methods to determine the level of layer sharing. This work proposes a novel method to assess the relatedness of tasks in a principled way. We base the relatedness of a task pair on the usefulness of a set of features of one task for the other, and vice versa. The resulting task affinities are used for the automated construction of a branched multi-task network in which deeper layers gradually grow more task-specific. Our multi-task network outperforms the state-of-the-art on CelebA. Additionally, the layer sharing schemes devised by our method outperform common multi-task learning models which were constructed ad hoc. We include additional experiments on Cityscapes and SUN RGB-D to illustrate the wide applicability of our approach. Code and trained models for this paper are made available this https URL
https://arxiv.org/abs/1904.02920
The complementary characteristics of active and passive depth sensing techniques motivate the fusion of the Li-DAR sensor and stereo camera for improved depth perception. Instead of directly fusing estimated depths across LiDAR and stereo modalities, we take advantages of the stereo matching network with two enhanced techniques: Input Fusion and Conditional Cost Volume Normalization (CCVNorm) on the LiDAR information. The proposed framework is generic and closely integrated with the cost volume component that is commonly utilized in stereo matching neural networks. We experimentally verify the efficacy and robustness of our method on the KITTI Stereo and Depth Completion datasets, obtaining favorable performance against various fusion strategies. Moreover, we demonstrate that, with a hierarchical extension of CCVNorm, the proposed method brings only slight overhead to the stereo matching network in terms of computation time and model size. For project page, see this https URL
https://arxiv.org/abs/1904.02917
While image manipulation achieves tremendous breakthroughs (e.g., generating realistic faces) in recent years, video generation is much less explored and harder to control, which limits its applications in the real world. For instance, video editing requires temporal coherence across multiple clips and thus poses both start and end constraints within a video sequence. We introduce point-to-point video generation that controls the generation process with two control points: the targeted start- and end-frames. The task is challenging since the model not only generates a smooth transition of frames, but also plans ahead to ensure that the generated end-frame conforms to the targeted end-frame for videos of various length. We propose to maximize the modified variational lower bound of conditional data likelihood under a skip-frame training strategy. Our model can generate sequences such that their end-frame is consistent with the targeted end-frame without loss of quality and diversity. Extensive experiments are conducted on Stochastic Moving MNIST, Weizmann Human Action, and Human3.6M to evaluate the effectiveness of the proposed method. We demonstrate our method under a series of scenarios (e.g., dynamic length generation) and the qualitative results showcase the potential and merits of point-to-point generation. For project page, see this https URL
https://arxiv.org/abs/1904.02912
Deconvolution microscopy has been extensively used to improve the resolution of the widefield fluorescent microscopy. Conventional approaches, which usually require the point spread function (PSF) measurement or blind estimation, are however computationally expensive. Recently, CNN based approaches have been explored as a fast and high performance alternative. In this paper, we present a novel unsupervised deep neural network for blind deconvolution based on cycle consistency and PSF modeling layers. In contrast to the recent CNN approaches for similar problem, the explicit PSF modeling layers improve the robustness of the algorithm. Experimental results confirm the efficacy of the algorithm.
https://arxiv.org/abs/1904.02910
Recently, deep image compression has shown a big progress in terms of coding efficiency and image quality improvement. However, relatively less attention has been put on video compression using deep learning networks. In the paper, we first propose a deep learning based bi-predictive coding network, called BP-DVC Net, for video compression. Learned from the lesson of the conventional video coding, a B-frame coding structure is incorporated in our BP-DVC Net. While the bi-predictive coding in the conventional video codecs requires to transmit to decoder sides the motion vectors for block motion and the residues from prediction, our BP-DVC Net incorporates optical flow estimation networks in both encoder and decoder sides so as not to transmit the motion information to the decoder sides for coding efficiency improvement. Also, a bi-prediction network in the BP-DVC Net is proposed and used to precisely predict the current frame and to yield the resulting residues as small as possible. Furthermore, our BP-DVC Net allows for the compressive feature maps to be entropy-coded using the temporal context among the feature maps of adjacent frames. The BP-DVC Net has an end-to-end video compression architecture with newly designed flow and prediction losses. Experimental results show that the compression performance of our proposed method is comparable to those of H.264, HEVC in terms of PSNR and MS-SSIM.
https://arxiv.org/abs/1904.02909
The application of deep learning (DL) models to neuroimaging data poses several challenges, due to the high dimensionality, low sample size and complex temporo-spatial dependency structure of these datasets. Even further, DL models act as as black-box models, impeding insight into the association of cognitive state and brain activity. To approach these challenges, we introduce the DeepLight framework, which utilizes long short-term memory (LSTM) based DL models to analyze whole-brain functional Magnetic Resonance Imaging (fMRI) data. To decode a cognitive state (e.g., seeing the image of a house), DeepLight separates the fMRI volume into a sequence of axial brain slices, which is then sequentially processed by an LSTM. To maintain interpretability, DeepLight adapts the layer-wise relevance propagation (LRP) technique. Thereby, decomposing its decoding decision into the contributions of the single input voxels to this decision. Importantly, the decomposition is performed on the level of single fMRI volumes, enabling DeepLight to study the associations between cognitive state and brain activity on several levels of data granularity, from the level of the group down to the level of single time points. To demonstrate the versatility of DeepLight, we apply it to a large fMRI dataset of the Human Connectome Project. We show that DeepLight outperforms conventional approaches of uni- and multivariate fMRI analysis in decoding the cognitive states and in identifying the physiologically appropriate brain regions associated with these states. We further demonstrate DeepLight’s ability to study the fine-grained temporo-spatial variability of brain activity over sequences of single fMRI samples.
http://arxiv.org/abs/1810.09945