Abstract | ||
---|---|---|
ABSTRACTRecent advances in unsupervised domain adaptation have achieved remarkable performance on semantic segmentation tasks. Despite such progress, existing works mainly focus on bridging the inter-domain gaps between the source and target domain, while only few of them noticed the intra-domain gaps within the target data. In this work, we propose a pixel-level intra-domain adaptation approach to reduce the intra-domain gaps within the target data. Compared with image-level methods, ours treats each pixel as an instance, which adapts the segmentation model at a more fine-grained level. Specifically, we first conduct the inter-domain adaptation between the source and target domain; Then, we separate the pixels in target images into the easy and hard subdomains; Finally, we propose a pixel-level adversarial training strategy to adapt a segmentation network from the easy to the hard subdomain. Moreover, we show that the segmentation accuracy can be further improved by incorporating a continuous indexing technique in the adversarial training. Experimental results show the effectiveness of our method against existing state-of-the-art approaches. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1145/3474085.3475174 | International Multimedia Conference |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zizheng Yan | 1 | 0 | 0.68 |
Xianggang Yu | 2 | 0 | 1.35 |
Yipeng Qin | 3 | 46 | 5.33 |
Yushuang Wu | 4 | 0 | 0.68 |
Xiaoguang Han | 5 | 0 | 0.34 |
Shuguang Cui | 6 | 521 | 54.46 |