SLAM: Semantic Learning based Activation Map for Weakly Supervised Semantic Segmentation

• URL: http://arxiv.org/abs/2210.12417v1
• Date: Sat, 22 Oct 2022 11:17:30 GMT
• Title: SLAM: Semantic Learning based Activation Map for Weakly Supervised Semantic Segmentation
• Authors: Junliang Chen, Xiaodong Zhao, Minmin Liu, Linlin Shen
• Abstract summary: We propose a novel semantic learning based framework for WSSS, named SLAM (Semantic Learning based Activation Map) We firstly design a semantic encoder to learn semantics of each object category and extract category-specific semantic embeddings from an input image. Four loss functions, i.e., category-foreground, category-background, activation regularization, and consistency loss are proposed to ensure the correctness, completeness, compactness and consistency of the activation map.
• Score: 34.996841532954925
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent mainstream weakly-supervised semantic segmentation (WSSS) approaches based on image-level annotations mainly relies on binary image-level classification with limited representation capacity. In this paper, we propose a novel semantic learning based framework for WSSS, named SLAM (Semantic Learning based Activation Map). We firstly design a semantic encoder to learn semantics of each object category and extract category-specific semantic embeddings from an input image. The semantic embeddings of foreground and background are then integrated to a segmentation network to learn the activation map. Four loss functions, i.e, category-foreground, category-background, activation regularization, and consistency loss are proposed to ensure the correctness, completeness, compactness and consistency of the activation map. Experimental results show that our semantic learning based SLAM achieves much better performance than binary image-level classification based approaches, i.e., around 3\% mIoU higher than OC-CSE \cite{occse}, CPN \cite{cpn} on PASCAL VOC dataset. Our SLAM also surpasses AMN \cite{amn} trained with strong per-pixel constraint and CLIMS \cite{clims} utilizing extra multi-modal knowledge. Code will be made available.

Related papers

• 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)
• SemPLeS: Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation [36.41778553250247]
  Weakly-Supervised Semantic (WSSS) aims to train segmentation models using image data with only image-level supervision. We propose a Semantic Prompt Learning for WSSS (SemPLeS) framework, which learns to effectively prompt the CLIP latent space. SemPLeS can perform better semantic alignment between object regions and the associated class labels.
  arXiv  Detail & Related papers  (2024-01-22T09:41:05Z)
• Advancing Incremental Few-shot Semantic Segmentation via Semantic-guided Relation Alignment and Adaptation [98.51938442785179]
  Incremental few-shot semantic segmentation aims to incrementally extend a semantic segmentation model to novel classes. This task faces a severe semantic-aliasing issue between base and novel classes due to data imbalance. We propose the Semantic-guided Relation Alignment and Adaptation (SRAA) method that fully considers the guidance of prior semantic information.
  arXiv  Detail & Related papers  (2023-05-18T10:40:52Z)
• ISLE: A Framework for Image Level Semantic Segmentation Ensemble [5.137284292672375]
  Conventional semantic segmentation networks require massive pixel-wise annotated labels to reach state-of-the-art prediction quality. We propose ISLE, which employs an ensemble of the "pseudo-labels" for a given set of different semantic segmentation techniques on a class-wise level. We reach up to 2.4% improvement over ISLE's individual components.
  arXiv  Detail & Related papers  (2023-03-14T13:36:36Z)
• Semantic Representation and Dependency Learning for Multi-Label Image Recognition [76.52120002993728]
  We propose a novel and effective semantic representation and dependency learning (SRDL) framework to learn category-specific semantic representation for each category. Specifically, we design a category-specific attentional regions (CAR) module to generate channel/spatial-wise attention matrices to guide model. We also design an object erasing (OE) module to implicitly learn semantic dependency among categories by erasing semantic-aware regions.
  arXiv  Detail & Related papers  (2022-04-08T00:55:15Z)
• A Simple Baseline for Zero-shot Semantic Segmentation with Pre-trained Vision-language Model [61.58071099082296]
  It is unclear how to make zero-shot recognition working well on broader vision problems, such as object detection and semantic segmentation. In this paper, we target for zero-shot semantic segmentation, by building it on an off-the-shelf pre-trained vision-language model, i.e., CLIP. Our experimental results show that this simple framework surpasses previous state-of-the-arts by a large margin.
  arXiv  Detail & Related papers  (2021-12-29T18:56:18Z)
• 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)
• Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation [128.03739769844736]
  Two neural co-attentions are incorporated into the classifier to capture cross-image semantic similarities and differences. In addition to boosting object pattern learning, the co-attention can leverage context from other related images to improve localization map inference. Our algorithm sets new state-of-the-arts on all these settings, demonstrating well its efficacy and generalizability.
  arXiv  Detail & Related papers  (2020-07-03T21:53:46Z)
• Discovering Latent Classes for Semi-Supervised Semantic Segmentation [18.5909667833129]
  This paper studies the problem of semi-supervised semantic segmentation. We learn latent classes consistent with semantic classes on labeled images. We show that the proposed method achieves state of the art results for semi-supervised semantic segmentation.
  arXiv  Detail & Related papers  (2019-12-30T14:16:24Z)

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.