CGViT: Cross-image GroupViT for zero-shot semantic segmentation
Authors:
- Jie JiangJJJie Jiang
- Xingjian HeXHXingjian He
- Xinxin ZhuXZXinxin Zhu
- Weining WangWWWeining Wang
- Jing LiuJLJing Liu
- 3 March 2025
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 164
Abstract
No abstract availableFunding Information
- National Major Science and Technology Projects of China (2023ZD0121201)
- Jiangsu Provincial Key Research and Development Program (BE2023016-3)
This publication has 28 references indexed in Scilit:
- Multi-query and multi-level enhanced network for semantic segmentationPattern Recognition, 2024
- Guided contrastive boundary learning for semantic segmentationPattern Recognition, 2024
- Improving CNN-based semantic segmentation on structurally similar data using contrastive graph convolutional networksPattern Recognition, 2024
- Frozen is better than learning: A new design of prototype-based classifier for semantic segmentationPattern Recognition, 2024
- Deep semantic segmentation of natural and medical images: a reviewArtificial Intelligence Review, 2020
- COCO-Stuff: Thing and Stuff Classes in Context2018
- Show and tell: A neural image caption generator2015
- Fully convolutional networks for semantic segmentation2015
- The Role of Context for Object Detection and Semantic Segmentation in the Wild2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009