Puzzle-CAM: Improved Localization Via Matching Partial And Full Features
Authors:
- 19 September 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 639-643
Abstract
Weakly-supervised semantic segmentation (WSSS) is introduced to narrow the gap for semantic segmentation performance from pixel-level supervision to image-level supervision. Most advanced approaches are based on class activation maps (CAMs) to generate pseudo-labels to train the segmentation network. The main limitation of WSSS is that the process of generating pseudo-labels from CAMs that use an image classifier is mainly focused on the most discriminative parts of the objects. To address this issue, we propose Puzzle-CAM, a process that minimizes differences between the features from separate patches and the whole image. Our method consists of a puzzle module and two regularization terms to discover the most integrated region in an object. Puzzle-CAM can activate the overall region of an object using image-level supervision without requiring extra parameters. In experiments, Puzzle-CAM outperformed previous state-of-the-art methods using the same labels for supervision on the PASCAL VOC 2012 dataset. Code associated with our experiments is available at https://github.com/OFRIN/PuzzleCAM.Keywords
All Related Versions
Funding Information
- National Research Foundation of Korea
This publication has 11 references indexed in Scilit:
- Learning Integral Objects With Intra-Class Discriminator for Weakly-Supervised Semantic Segmentation2020
- Weakly Supervised Learning of Instance Segmentation With Inter-Pixel Relations2019
- FickleNet: Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic Inference2019
- Learning Pixel-Level Semantic Affinity with Image-Level Supervision for Weakly Supervised Semantic Segmentation2018
- Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing2018
- Simple Does It: Weakly Supervised Instance and Semantic Segmentation2017
- Learning Deep Features for Discriminative Localization2016
- Fully convolutional networks for semantic segmentation2015
- Semantic contours from inverse detectors2011
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009