• Home
  • Search
  • SAL:Selection and Attention Losses for Weakly Supervised Semantic Segmentation
  • Cite Icon57
  • https://doi.org/10.1109/tmm.2020.2991592Copy DOI Icon

SAL:Selection and Attention Losses for Weakly Supervised Semantic Segmentation

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Training a fully supervised semantic segmentation network requires a large amount of expensive pixel-level annotations in manual labor. In this work, we focus on studying the semantic segmentation problem using only image-level supervision. An effective scheme for weakly supervised segmentation is employed to produce the proxy annotations via image tags firstly. Then the segmentation network is retrained on the generated noisy proxy annotations. However, learning from noisy annotations is risky, as proxy annotations of poor quality may deteriorate the performance of the baseline segmentation and classification networks. In order to train the segmentation network using noisy annotations more effectively, two novel loss functions are proposed in this paper, namely, the selection loss and attention loss. Firstly, a selection loss is designed by weighting the proxy annotations based on a coarse-to-fine strategy for evaluating the quality of segmentation masks. Secondly, an attention loss taking the clean image tags as supervision is utilized to correct the classification errors caused by ambiguous pixel-level labels. Finally, we propose an end-to-end semantic segmentation network SAL-Net guided by the above two losses. From the extensive experiments conducted on PASCAL VOC 2012 dataset, SAL-Net reaches state-of-the-art performance with mean IoU (mIoU) as 62.5% and 66.6% on the test set by taking VGG16 network and ResNet101 network as the baselines respectively, which demonstrates the superiority of the proposed algorithm over eight representative weakly supervised segmentation methods. The code and models are available at https://github.com/zmbhou/SALTMM.

Similar Papers
  • Research Article
  • Citations6

Weakly supervised semantic segmentation by knowledge graph inference

  • Sep 11, 2024
  • Engineering Applications of Artificial Intelligence
  • Jia Zhang +3
  • Research Article

MPSS: A Model Pruning Method for Semantic Image Segmentation Networks

  • Jan 01, 2026
  • IEEE Transactions on Multimedia
  • Yeqiang Qian +3
  • Conference Article
  • Citations141

Multi-Scale Multi-Task FCN for Semantic Page Segmentation and Table Detection

  • Nov 01, 2017
  • Dafang He +4
  • Research Article
  • Citations153

Weakly Supervised Semantic Segmentation Using Superpixel Pooling Network

  • Feb 12, 2017
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Suha Kwak +2
  • Book Chapter
  • Citations8

MLAttack: Fooling Semantic Segmentation Networks by Multi-layer Attacks

  • Jan 01, 2019
  • Puneet Gupta +1
  • Research Article
  • Citations48

Improving RGB-D SLAM accuracy in dynamic environments based on semantic and geometric constraints

  • May 26, 2023
  • Measurement
  • Xiqi Wang +3
  • PDF
  • Research Article
  • Citations8

Cross-validation of a semantic segmentation network for natural history collection specimens

  • Mar 21, 2022
  • Machine Vision and Applications
  • Abraham Nieva De La Hidalga +10
  • Research Article
  • Citations4

A Unified Architecture of Semantic Segmentation and Hierarchical Generative Adversarial Networks for Expression Manipulation

  • Jan 01, 2022
  • SSRN Electronic Journal
  • Rumeysa Bodur +2
  • Research Article
  • Citations19

Erase then grow: Generating correct class activation maps for weakly-supervised semantic segmentation

  • Apr 30, 2021
  • Neurocomputing
  • Yanwen Chong +3
  • PDF
  • Research Article
  • Citations13

Real-Time Semantic Understanding and Segmentation of Urban Scenes for Vehicle Visual Sensors by Optimized DCNN Algorithm

  • Aug 03, 2022
  • Applied Sciences
  • Yanyi Li +2
  • Research Article
  • Citations97

SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network

  • May 18, 2021
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Mingmei Cheng +3
  • Research Article
  • Citations5

KDOSS-net: Knowledge distillation-based outpainting and semantic segmentation network for crop and weed images

  • Aug 20, 2025
  • Plant Phenomics
  • Sang Hyo Cheong +4
  • Research Article
  • Citations2

Training and inference for integer-based semantic segmentation network

  • May 04, 2021
  • Neurocomputing
  • Jiayi Yang +4
  • PDF
  • Research Article
  • Citations127

Chest X-ray pneumothorax segmentation using U-Net with EfficientNet and ResNet architectures.

  • Jun 29, 2021
  • PeerJ. Computer science
  • Ayat Abedalla +3
  • PDF
  • Book Chapter
  • Citations42

NNV 2.0: The Neural Network Verification Tool

  • Jan 01, 2023
  • Diego Manzanas Lopez +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.