{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/logits-deconfusion-with-clip-for-few-shot","title":"Logits DeConfusion with CLIP for Few-Shot Learning","arxiv_id":"2504.12104","date":"2025-04-16","proceeding":"CVPR 2025 1","authors":["Shuo Li","Fang Liu","Zehua Hao","Xinyi Wang","Lingling Li","Xu Liu","Puhua Chen","Wenping Ma"],"abstract":"With its powerful visual-language alignment capability, CLIP performs well in zero-shot and few-shot learning tasks. However, we found in experiments that CLIP's logits suffer from serious inter-class confusion problems in downstream tasks, and the ambiguity between categories seriously affects the accuracy. To address this challenge, we propose a novel method called Logits DeConfusion, which effectively learns and eliminates inter-class confusion in logits by combining our Multi-level Adapter Fusion (MAF) module with our Inter-Class Deconfusion (ICD) module. Our MAF extracts features from different levels and fuses them uniformly to enhance feature representation. Our ICD learnably eliminates inter-class confusion in logits with a residual structure. Experimental results show that our method can significantly improve the classification performance and alleviate the inter-class confusion problem. The code is available at https://github.com/LiShuo1001/LDC.","url_abs":"https://arxiv.org/abs/2504.12104v1","url_pdf":"https://arxiv.org/pdf/2504.12104v1.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":"logits-deconfusion-with-clip-for-few-shot","repo_url":"https://github.com/lishuo1001/ldc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2504.12104","atlas_url":"https://app.syntology.ai/?focus=2504.12104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.12104"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/LiShuo1001/LDC","reach":null}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":7,"samples":[{"code_sha256_prefix":"bf4da34874ce98df","entry":"LayerNorm","repo":"LiShuo1001/LDC","repo_kind":"official","path":"clip_ldc/model.py","file_url":"https://github.com/LiShuo1001/LDC/blob/HEAD/clip_ldc/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bf4da34874ce98df"}},{"code_sha256_prefix":"2aeba1d2520051c5","entry":"ModifiedResNet","repo":"LiShuo1001/LDC","repo_kind":"official","path":"clip_ldc/model.py","file_url":"https://github.com/LiShuo1001/LDC/blob/HEAD/clip_ldc/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2aeba1d2520051c5"}},{"code_sha256_prefix":"d42d9efb07661959","entry":"PatchMean","repo":"LiShuo1001/LDC","repo_kind":"official","path":"clip_ldc/model.py","file_url":"https://github.com/LiShuo1001/LDC/blob/HEAD/clip_ldc/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d42d9efb07661959"}},{"code_sha256_prefix":"7279d08798402859","entry":"ResidualAttentionBlock","repo":"LiShuo1001/LDC","repo_kind":"official","path":"clip_ldc/model.py","file_url":"https://github.com/LiShuo1001/LDC/blob/HEAD/clip_ldc/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7279d08798402859"}},{"code_sha256_prefix":"88a3a0b4a7b5fb2a","entry":"Transformer","repo":"LiShuo1001/LDC","repo_kind":"official","path":"clip_ldc/model.py","file_url":"https://github.com/LiShuo1001/LDC/blob/HEAD/clip_ldc/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"88a3a0b4a7b5fb2a"}},{"code_sha256_prefix":"1c4c241386ee3fe2","entry":"VisionTransformer","repo":"LiShuo1001/LDC","repo_kind":"official","path":"clip_ldc/model.py","file_url":"https://github.com/LiShuo1001/LDC/blob/HEAD/clip_ldc/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1c4c241386ee3fe2"}},{"code_sha256_prefix":"65fe97557e0cb835","entry":"CLIP","repo":"LiShuo1001/LDC","repo_kind":"official","path":"clip_ldc/model.py","file_url":"https://github.com/LiShuo1001/LDC/blob/HEAD/clip_ldc/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"65fe97557e0cb835"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}