papers AI Learner
The Github is limit! Click to go to the new site.

CODA: Counting Objects via Scale-aware Adversarial Density Adaption

2019-03-25
Li Wang, Yongbo Li, Xiangyang Xue

Abstract

Recent advances in crowd counting have achieved promising results with increasingly complex convolutional neural network designs. However, due to the unpredictable domain shift, generalizing trained model to unseen scenarios is often suboptimal. Inspired by the observation that density maps of different scenarios share similar local structures, we propose a novel adversarial learning approach in this paper, i.e., CODA (\emph{Counting Objects via scale-aware adversarial Density Adaption}). To deal with different object scales and density distributions, we perform adversarial training with pyramid patches of multi-scales from both source- and target-domain. Along with a ranking constraint across levels of the pyramid input, consistent object counts can be produced for different scales. Extensive experiments demonstrate that our network produces much better results on unseen datasets compared with existing counting adaption models. Notably, the performance of our CODA is comparable with the state-of-the-art fully-supervised models that are trained on the target dataset. Further analysis indicates that our density adaption framework can effortlessly extend to scenarios with different objects. \emph{The code is available at https://github.com/Willy0919/CODA.}

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.10442

PDF

http://arxiv.org/pdf/1903.10442


Similar Posts

Comments