Know Your Attention Maps: Class-specific Token Masking for Weakly Supervised Semantic Segmentation

• URL: http://arxiv.org/abs/2507.06848v1
• Date: Wed, 09 Jul 2025 13:53:34 GMT
• Title: Know Your Attention Maps: Class-specific Token Masking for Weakly Supervised Semantic Segmentation
• Authors: Joelle Hanna, Damian Borth,
• Abstract summary: We propose an end-to-end method that directly utilizes the attention maps learned by a Transformer Vision (ViT) for Weakly Supervised Semantics (WSSS)<n>At inference time, we aggregate the different self-attention maps of each [] token corresponding to the predicted labels to generate pseudo segmentation masks.
• Score: 5.824064631226058
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Weakly Supervised Semantic Segmentation (WSSS) is a challenging problem that has been extensively studied in recent years. Traditional approaches often rely on external modules like Class Activation Maps to highlight regions of interest and generate pseudo segmentation masks. In this work, we propose an end-to-end method that directly utilizes the attention maps learned by a Vision Transformer (ViT) for WSSS. We propose training a sparse ViT with multiple [CLS] tokens (one for each class), using a random masking strategy to promote [CLS] token - class assignment. At inference time, we aggregate the different self-attention maps of each [CLS] token corresponding to the predicted labels to generate pseudo segmentation masks. Our proposed approach enhances the interpretability of self-attention maps and ensures accurate class assignments. Extensive experiments on two standard benchmarks and three specialized datasets demonstrate that our method generates accurate pseudo-masks, outperforming related works. Those pseudo-masks can be used to train a segmentation model which achieves results comparable to fully-supervised models, significantly reducing the need for fine-grained labeled data.

Related papers

• Bridge the Points: Graph-based Few-shot Segment Anything Semantically [79.1519244940518]
  Recent advancements in pre-training techniques have enhanced the capabilities of vision foundation models. Recent studies extend the SAM to Few-shot Semantic segmentation (FSS) We propose a simple yet effective approach based on graph analysis.
  arXiv  Detail & Related papers  (2024-10-09T15:02:28Z)
• MaskUno: Switch-Split Block For Enhancing Instance Segmentation [0.0]
  We propose replacing mask prediction with a Switch-Split block that processes refined ROIs, classifies them, and assigns them to specialized mask predictors. An increase in the mean Average Precision (mAP) of 2.03% was observed for the high-performing DetectoRS when trained on 80 classes.
  arXiv  Detail & Related papers  (2024-07-31T10:12:14Z)
• Auxiliary Tasks Enhanced Dual-affinity Learning for Weakly Supervised Semantic Segmentation [79.05949524349005]
  We propose AuxSegNet+, a weakly supervised auxiliary learning framework to explore the rich information from saliency maps. We also propose a cross-task affinity learning mechanism to learn pixel-level affinities from the saliency and segmentation feature maps.
  arXiv  Detail & Related papers  (2024-03-02T10:03:21Z)
• Exploiting Shape Cues for Weakly Supervised Semantic Segmentation [15.791415215216029]
  Weakly supervised semantic segmentation (WSSS) aims to produce pixel-wise class predictions with only image-level labels for training. We propose to exploit shape information to supplement the texture-biased property of convolutional neural networks (CNNs) We further refine the predictions in an online fashion with a novel refinement method that takes into account both the class and the color affinities.
  arXiv  Detail & Related papers  (2022-08-08T17:25:31Z)
• What You See is What You Classify: Black Box Attributions [61.998683569022006]
  We train a deep network, the Explainer, to predict attributions for a pre-trained black-box classifier, the Explanandum. Unlike most existing approaches, ours is capable of directly generating very distinct class-specific masks. We show that our attributions are superior to established methods both visually and quantitatively.
  arXiv  Detail & Related papers  (2022-05-23T12:30:04Z)
• Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation [88.49669148290306]
  We propose a novel weakly supervised multi-task framework called AuxSegNet to leverage saliency detection and multi-label image classification as auxiliary tasks. 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.
  arXiv  Detail & Related papers  (2021-07-25T11:39:58Z)
• Per-Pixel Classification is Not All You Need for Semantic Segmentation [184.2905747595058]
  Mask classification is sufficiently general to solve both semantic- and instance-level segmentation tasks. We propose MaskFormer, a simple mask classification model which predicts a set of binary masks. Our method outperforms both current state-of-the-art semantic (55.6 mIoU on ADE20K) and panoptic segmentation (52.7 PQ on COCO) models.
  arXiv  Detail & Related papers  (2021-07-13T17:59:50Z)
• Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation [156.9155100983315]
  We seek for a more accurate learning-based class-agnostic pseudo mask generator tailored to box-supervised semantic segmentation. Our method can further close the performance gap between box-supervised and fully-supervised models.
  arXiv  Detail & Related papers  (2021-03-09T14:54:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.