Open AccessPosted Content
Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
Reads0
Chats0
TLDR
A category-level adversarial network is introduced, aiming to enforce local semantic consistency during the trend of global alignment, to take a close look at the category- level data distribution and align each class with an adaptive adversarial loss.Abstract:
We consider the problem of unsupervised domain adaptation in semantic segmentation. The key in this campaign consists in reducing the domain shift, i.e., enforcing the data distributions of the two domains to be similar. A popular strategy is to align the marginal distribution in the feature space through adversarial learning. However, this global alignment strategy does not consider the local category-level feature distribution. A possible consequence of the global movement is that some categories which are originally well aligned between the source and target may be incorrectly mapped. To address this problem, this paper introduces a category-level adversarial network, aiming to enforce local semantic consistency during the trend of global alignment. Our idea is to take a close look at the category-level data distribution and align each class with an adaptive adversarial loss. Specifically, we reduce the weight of the adversarial loss for category-level aligned features while increasing the adversarial force for those poorly aligned. In this process, we decide how well a feature is category-level aligned between source and target by a co-training approach. In two domain adaptation tasks, i.e., GTA5 -> Cityscapes and SYNTHIA -> Cityscapes, we validate that the proposed method matches the state of the art in segmentation accuracy.read more
Citations
More filters
Proceedings ArticleDOI
Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration
TL;DR: He et al. as discussed by the authors proposed a filter pruning via geometric median (FPGM) method to compress CNN models by pruning filters with redundancy, rather than those with relatively less importance.
Proceedings ArticleDOI
Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-Identification
TL;DR: Zhun et al. as discussed by the authors proposed an exemplar memory to store features of the target domain and accommodate the three invariance properties, i.e., exemplar-invariance, camera invariance, and neighborhood invariance.
Proceedings ArticleDOI
Pose-Guided Feature Alignment for Occluded Person Re-Identification
TL;DR: This paper introduces a novel method named Pose-Guided Feature Alignment (PGFA), exploiting pose landmarks to disentangle the useful information from the occluded noise, and largely outperforms existing person re-id methods on three occlusion datasets, while remains top performance on two holistic datasets.
Proceedings ArticleDOI
FDA: Fourier Domain Adaptation for Semantic Segmentation
Yanchao Yang,Stefano Soatto +1 more
TL;DR: A simple method for unsupervised domain adaptation, whereby the discrepancy between the source and target distributions is reduced by swapping the low-frequency spectrum of one with the other, which results indicate that even simple procedures can discount nuisance variability in the data that more sophisticated methods struggle to learn away.
Proceedings ArticleDOI
DLOW: Domain Flow for Adaptation and Generalization
TL;DR: A domain flow generation model to bridge two different domains by generating a continuous sequence of intermediate domains flowing from one domain to the other and demonstrating the effectiveness of the model for both cross-domain semantic segmentation and the style generalization tasks on benchmark datasets is presented.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.