{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/exploring-visual-interpretability-for","title":"Exploring Visual Interpretability for Contrastive Language-Image Pre-training","arxiv_id":"2209.07046","date":"2022-09-15","proceeding":null,"authors":["Yi Li","Hualiang Wang","Yiqun Duan","Hang Xu","Xiaomeng Li"],"abstract":"Contrastive Language-Image Pre-training (CLIP) learns rich representations via readily available supervision of natural language. It improves the performance of downstream vision tasks, including but not limited to the zero-shot, long tail, segmentation, retrieval, caption, and video. However, the visual explainability of CLIP is rarely studied, especially for the raw feature map. To provide visual explanations of its predictions, we propose the Image-Text Similarity Map (ITSM). Based on it, we surprisingly find that CLIP prefers the background regions than the foregrounds, and shows erroneous visualization results against human understanding. This phenomenon is universal for both vision transformers and convolutional networks, which suggests this problem is unique and not owing to certain network. Experimentally, we find the devil is in the pooling part, where inappropriate pooling methods lead to a phenomenon called semantic shift. For this problem, we propose the Explainable Contrastive Language-Image Pre-training (ECLIP), which corrects the explainability via the Masked Max Pooling. Specifically, to avoid the semantic shift, we replace the original attention pooling by max pooling to focus on the confident foreground, with guidance from free attention during training. Experiments on three datasets suggest that ECLIP greatly improves the explainability of CLIP, and beyond previous explainability methods at large margins. The code will be released later.","url_abs":"https://arxiv.org/abs/2209.07046v2","url_pdf":"https://arxiv.org/pdf/2209.07046v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"exploring-visual-interpretability-for","repo_url":"https://github.com/xmed-lab/iclip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-similarity","task_name":"text similarity"}],"methods":[{"method_slug":"attention-pooling","method_name":"Attention Pooling"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"max-pooling","method_name":"Max Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.07046","atlas_url":"https://app.syntology.ai/?focus=2209.07046","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2209.07046"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2209.07046\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2209.07046"},"call":"get_concepts_for_paper(arxiv_id=\"2209.07046\")"}],"by_repo":[{"repo":"xmed-lab/iclip","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"33410d730a9c9e363de45c50df7ae0cf0a814f80ba6b6a402ff2ed1945d99574","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}