ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation
- 22 August 2025
- journal article
- research article
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (11) , 7946-7968
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (92370114)
This publication has 56 references indexed in Scilit:
- ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference2024
- SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference2024
- SLIP: Self-supervision Meets Language-Image Pre-training2022
- Scaling Open-Vocabulary Image Segmentation with Image-Level Labels2022
- Extract Free Dense Labels from CLIP2022
- Autoregressive Unsupervised Image Segmentation2020
- SCAN: Learning to Classify Images Without Labels2020
- UNITER: UNiversal Image-TExt Representation Learning2020
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955