Timezone: »

 
Poster
Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation
Qiming ZHANG · Jing Zhang · Wei Liu · Dacheng Tao

Wed Dec 11 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #76
in Applications -- Image Segmentation »
Unsupervised domain adaptation (UDA) aims to enhance the generalization capability of a certain model from a source domain to a target domain. UDA is of particular significance since no extra effort is devoted to annotating target domain samples. However, the different data distributions in the two domains, or \emph{domain shift/discrepancy}, inevitably compromise the UDA performance. Although there has been a progress in matching the marginal distributions between two domains, the classifier favors the source domain features and makes incorrect predictions on the target domain due to category-agnostic feature alignment. In this paper, we propose a novel category anchor-guided (CAG) UDA model for semantic segmentation, which explicitly enforces category-aware feature alignment to learn shared discriminative features and classifiers simultaneously. First, the category-wise centroids of the source domain features are used as guided anchors to identify the active features in the target domain and also assign them pseudo-labels. Then, we leverage an anchor-based pixel-level distance loss and a discriminative loss to drive the intra-category features closer and the inter-category features further apart, respectively. Finally, we devise a stagewise training mechanism to reduce the error accumulation and adapt the proposed model progressively. Experiments on both the GTA5$\rightarrow $Cityscapes and SYNTHIA$\rightarrow $Cityscapes scenarios demonstrate the superiority of our CAG-UDA model over the state-of-the-art methods. The code is available at \url{https://github.com/RogerZhangzz/CAG\_UDA}.
Keywords: Multitask and Transfer Learning · Image Segmentation · Algorithms · Algorithms -> Unsupervised Learning; Applications
[ Paper]  [ Poster] 

Author Information

Qiming ZHANG (University of Sydney)
Jing Zhang (The University of Sydney)
Wei Liu (Tencent AI Lab)
Dacheng Tao (University of Sydney)

More from the Same Authors