Pixel-level intra-domain adaptation for semantic segmentation

Yan, Zizheng, Yu, Xianggang, Qin, Yipeng ORCID: https://orcid.org/0000-0002-1551-9126, Wu, Yushuang, Han, Xiaoguang and Cui, Shuguang 2021. Pixel-level intra-domain adaptation for semantic segmentation. Presented at: ACM Multimedia 2021, Chengdu, China, 20-24 October 2021. MM '21: Proceedings of the 29th ACM International Conference on Multimedia. ACM, pp. 404-413. 10.1145/3474085.3475174

PDF - Accepted Post-Print Version Download (5MB)

Abstract

Recent 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.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	ACM
Date of First Compliant Deposit:	9 August 2021
Date of Acceptance:	4 July 2021
Last Modified:	09 Nov 2022 11:25
URI:	https://orca.cardiff.ac.uk/id/eprint/143144

Actions (repository staff only)

Edit Item