期刊
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
卷 -, 期 -, 页码 6964-6973出版社
IEEE
DOI: 10.1109/ICCV48922.2021.00690
关键词
-
资金
- Australian Research Council [DP150100294, DP150104251, DP200103223]
- Australian Medical Research Future Fund [MR-FAI000085]
- Early Career Scheme of the Research Grants Council (RGC) of the Hong Kong SAR [26202321]
- HKUST Startup Fund [R9253]
The proposed AuxSegNet framework leverages saliency detection and multi-label image classification as auxiliary tasks to improve the primary task of semantic segmentation. By learning a cross-task global pixel-level affinity map, the method effectively enhances saliency predictions and provides improved pseudo labels for segmentation tasks.
Semantic segmentation is a challenging task in the absence of densely labelled data. Only relying on class activation maps (CAM) with image-level labels provides deficient segmentation supervision. Prior works thus consider pre-trained models to produce coarse saliency maps to guide the generation of pseudo segmentation labels. However, the commonly used off-line heuristic generation process cannot fully exploit the benefits of these coarse saliency maps. Motivated by the significant inter-task correlation, we propose a novel weakly supervised multi-task framework termed as AuxSegNet, to leverage saliency detection and multi-label image classification as auxiliary tasks to improve the primary task of semantic segmentation using only image-level ground-truth labels. Inspired by their similar structured semantics, we also propose to learn a cross-task global pixel-level affinity map from the saliency and segmentation representations. The learned cross-task affinity can be used to refine saliency predictions and propagate CAM maps to provide improved pseudo labels for both tasks. The mutual boost between pseudo label updating and cross-task affinity learning enables iterative improvements on segmentation performance. Extensive experiments demonstrate the effectiveness of the proposed auxiliary learning network structure and the cross-task affinity learning method. The proposed approach achieves state-of-the-art weakly supervised segmentation performance on the challenging PASCAL VOC 2012 and MS COCO benchmarks.(1)
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据