Image-level weakly supervised semantic segmentation has received increasing attention due to its low annotation cost. Existing methods mainly rely on Class Activation Mapping …
B Zhang, S Yu, Y Wei, Y Zhao… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Weakly supervised semantic segmentation has witnessed great achievements with image- level labels. Several recent approaches use the CLIP model to generate pseudo labels for …
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 …
T Zhang, G Lin, W Liu, J Cai, A Kot - … , Glasgow, UK, August 23–28, 2020 …, 2020 - Springer
In this paper we focus on the task of weakly-supervised semantic segmentation supervised with image-level labels. Since the pixel-level annotation is not available in the training …
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 …
L Zhu, H He, X Zhang, Q Chen, S Zeng, Q Ren… - arXiv preprint arXiv …, 2023 - arxiv.org
End-to-end weakly supervised semantic segmentation aims at optimizing a segmentation model in a single-stage training process based on only image annotations. Existing methods …
In this paper, we aim to tackle semi-and-weakly supervised semantic segmentation (SWSSS), where many image-level classification labels and a few pixel-level annotations …
Abstract For Weakly-Supervised Semantic Segmentation (WSSS) with image-level annotation, mostly relies on the classification network to generate initial segmentation …
Great progress has been witnessed for weakly supervised semantic segmentation, which aims to segment objects without dense pixel annotations. Most approaches concentrate on …