Extracting class activation maps from non-discriminative features as well
Extracting class activation maps (CAM) from a classification model often results in poor
coverage on foreground objects, ie, only the discriminative region (eg, the" head" of" sheep") …
coverage on foreground objects, ie, only the discriminative region (eg, the" head" of" sheep") …
Out-of-candidate rectification for weakly supervised semantic segmentation
Weakly supervised semantic segmentation is typically inspired by class activation maps,
which serve as pseudo masks with class-discriminative regions highlighted. Although …
which serve as pseudo masks with class-discriminative regions highlighted. Although …
Weakly supervised semantic segmentation via adversarial learning of classifier and reconstructor
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 …
(CAMs) usually 1) do not cover the whole object and 2) be activated on irrelevant regions …
Weakly-supervised semantic segmentation with image-level labels: from traditional models to foundation models
The rapid development of deep learning has driven significant progress in the field of image
semantic segmentation-a fundamental task in computer vision. Semantic segmentation …
semantic segmentation-a fundamental task in computer vision. Semantic segmentation …
Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation has witnessed great achievements with image-
level labels. Several recent approaches use the CLIP model to generate pseudo labels for …
level labels. Several recent approaches use the CLIP model to generate pseudo labels for …
From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation
Abstract Weakly Supervised Semantic Segmentation (WSSS) aims to learn the concept of
segmentation using image-level class labels. Recent WSSS works have shown promising …
segmentation using image-level class labels. Recent WSSS works have shown promising …
Class Tokens Infusion for Weakly Supervised Semantic Segmentation
Abstract Weakly Supervised Semantic Segmentation (WSSS) relies on Class Activation
Maps (CAMs) to extract spatial information from image-level labels. With the success of …
Maps (CAMs) to extract spatial information from image-level labels. With the success of …
Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation
Recent weakly supervised semantic segmentation (WSSS) methods strive to incorporate
contextual knowledge to improve the completeness of class activation maps (CAM). In this …
contextual knowledge to improve the completeness of class activation maps (CAM). In this …
Prompting classes: exploring the power of prompt class learning in weakly supervised semantic segmentation
B Murugesan, R Hussain… - Proceedings of the …, 2024 - openaccess.thecvf.com
Recently, CLIP-based approaches have exhibited remarkable performance on
generalization and few-shot learning tasks, fueled by the power of contrastive language …
generalization and few-shot learning tasks, fueled by the power of contrastive language …
Branches mutual promotion for end-to-end weakly supervised semantic segmentation
End-to-end weakly supervised semantic segmentation (E2E-WSSS) aims at optimizing a
segmentation model in a single-stage training process based on only image annotations …
segmentation model in a single-stage training process based on only image annotations …