Y Lin, M Chen, W Wang, B Wu, K Li… - Proceedings of the …, 2023 - openaccess.thecvf.com
Weakly supervised semantic segmentation (WSSS) with image-level labels is a challenging task. Mainstream approaches follow a multi-stage framework and suffer from high training …
S Rong, B Tu, Z Wang, J Li - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
The existing weakly supervised semantic segmentation (WSSS) methods pay much attention to generating accurate and complete class activation maps (CAMs) as pseudo …
Z Cheng, P Qiao, K Li, S Li, P Wei, X Ji… - Proceedings of the …, 2023 - openaccess.thecvf.com
Weakly supervised semantic segmentation is typically inspired by class activation maps, which serve as pseudo masks with class-discriminative regions highlighted. Although …
Abstract In Weakly Supervised Semantic Segmentation (WSSS), Class Activation Maps (CAMs) usually 1) do not cover the whole object and 2) be activated on irrelevant regions …
S Jo, IJ Yu, K Kim - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Weakly-supervised semantic segmentation aims to reduce labeling costs by training semantic segmentation models using weak supervision, such as image-level class labels …
W Sun, Y Zhang, Z Qin, Z Liu… - Proceedings of the …, 2023 - openaccess.thecvf.com
In this work, we propose a new transformer-based regularization to better localize objects for Weakly supervised semantic segmentation (WSSS). In image-level WSSS, Class Activation …
L Zhu, Y Li, J Fang, Y Liu, H Xin, W Liu… - arXiv preprint arXiv …, 2023 - arxiv.org
This paper explores the properties of the plain Vision Transformer (ViT) for Weakly- supervised Semantic Segmentation (WSSS). The class activation map (CAM) is of critical …
J Feng, X Wang, T Li, S Ji, W Liu - Pattern Recognition Letters, 2023 - Elsevier
Many existing weakly-supervised semantic segmentation methods focus on obtaining more accurate pseudo-masks with weak labels. So far pseudo-masks have come close to the …
Z Li, X Zhang, P Xiao - IEEE Transactions on Geoscience and …, 2023 - ieeexplore.ieee.org
Semantic segmentation of remote sensing images (RSIs) is effective for large-scale land cover mapping, which heavily relies on a large amount of training data with laborious pixel …