{"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/transagent-transfer-vision-language","title":"TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration","arxiv_id":"2410.12183","date":"2024-10-16","proceeding":null,"authors":["Yiwei Guo","Shaobin Zhuang","Kunchang Li","Yu Qiao","Yali Wang"],"abstract":"Vision-language foundation models (such as CLIP) have recently shown their power in transfer learning, owing to large-scale image-text pre-training. However, target domain data in the downstream tasks can be highly different from the pre-training phase, which makes it hard for such a single model to generalize well. Alternatively, there exists a wide range of expert models that contain diversified vision and/or language knowledge pre-trained on different modalities, tasks, networks, and datasets. Unfortunately, these models are \"isolated agents\" with heterogeneous structures, and how to integrate their knowledge for generalizing CLIP-like models has not been fully explored. To bridge this gap, we propose a general and concise TransAgent framework, which transports the knowledge of the isolated agents in a unified manner, and effectively guides CLIP to generalize with multi-source knowledge distillation. With such a distinct framework, we flexibly collaborate with 11 heterogeneous agents to empower vision-language foundation models, without further cost in the inference phase. Finally, our TransAgent achieves state-of-the-art performance on 11 visual recognition datasets. Under the same low-shot setting, it outperforms the popular CoOp with around 10% on average, and 20% on EuroSAT which contains large domain shifts.","url_abs":"https://arxiv.org/abs/2410.12183v2","url_pdf":"https://arxiv.org/pdf/2410.12183v2.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":"transagent-transfer-vision-language","repo_url":"https://github.com/markywg/transagent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"coop","method_name":"CoOp"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.12183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12183"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/markywg/transagent","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"98f385d847636a3e","entry":"basic_clean","repo":"markywg/transagent","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/markywg/transagent/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"ba26afd892405335","entry":"compute_ci95","repo":"markywg/transagent","repo_kind":"official","path":"parse_test_res.py","file_url":"https://github.com/markywg/transagent/blob/HEAD/parse_test_res.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ba26afd892405335"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"markywg/transagent","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/markywg/transagent/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"58b9c07e953aa9e3","entry":"normalize","repo":"markywg/transagent","repo_kind":"official","path":"trainers/transagent.py","file_url":"https://github.com/markywg/transagent/blob/HEAD/trainers/transagent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58b9c07e953aa9e3"}},{"code_sha256_prefix":"5867829922dda909","entry":"normalize_sam","repo":"markywg/transagent","repo_kind":"official","path":"trainers/transagent.py","file_url":"https://github.com/markywg/transagent/blob/HEAD/trainers/transagent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5867829922dda909"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"markywg/transagent","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/markywg/transagent/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"f0840704676fc37a","entry":"build_model","repo":"markywg/transagent","repo_kind":"official","path":"clip/model.py","file_url":"https://github.com/markywg/transagent/blob/HEAD/clip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f0840704676fc37a"}},{"code_sha256_prefix":"605c4103ee2cd07b","entry":"load","repo":"markywg/transagent","repo_kind":"official","path":"clip/clip.py","file_url":"https://github.com/markywg/transagent/blob/HEAD/clip/clip.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"605c4103ee2cd07b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}