Papers › A Closer Look at the Explainability of Contrastive Language-Image Pre-training
A Closer Look at the Explainability of Contrastive Language-Image Pre-training
Yi Li, Hualiang Wang, Yiqun Duan, Jiheng Zhang, Xiaomeng Li
Contrastive language-image pre-training (CLIP) is a powerful vision-language model that has shown great benefits for various tasks. However, we have identified some issues with its explainability, which undermine its credibility and limit the capacity for related tasks. Specifically, we find that CLIP tends to focus on background regions rather than foregrounds, with noisy activations at irrelevant positions on the visualization results. These phenomena conflict with conventional explainability methods based on the class attention map (CAM), where the raw model can highlight the local foreground regions using global supervision without alignment. To address these problems, we take a closer look at its architecture and features. Based on thorough analyses, we find the raw self-attentions link to inconsistent semantic regions, resulting in the opposite visualization. Besides, the noisy activations are owing to redundant features among categories. Building on these insights, we propose the CLIP Surgery for reliable CAM, a method that allows surgery-like modifications to the inference architecture and features, without further fine-tuning as classical CAM methods. This approach significantly improves the explainability of CLIP, surpassing existing methods by large margins. Besides, it enables multimodal visualization and extends the capacity of raw CLIP on open-vocabulary tasks without extra alignment. The code is available at https://github.com/xmed-lab/CLIP_Surgery.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="2304.05653", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2304.05653")
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Open Vocabulary Semantic Segmentation | COCO-Stuff-171 | CLIP Surgery (original CLIP without any fine-tuning) | mIoU | 21.9 | #6 of 7 | Archive leaderboard | report |
| Open Vocabulary Semantic Segmentation | Cityscapes | CLIP Surgery (CLIP without any fine-tuning) | mIoU | 31.4 | #4 of 5 | Archive leaderboard | report |
| Open Vocabulary Semantic Segmentation | PASCAL Context-59 | CLIP Surgery (original CLIP without any fine-tuning) | mIoU | 29.3 | #24 of 24 | Archive leaderboard | report |
| Zero Shot Segmentation | ADE20K training-free zero-shot segmentation | CLIPSurgery | mIoU | 12.9 | #4 of 5 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections