{"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/chameleon-a-data-efficient-generalist-for","title":"Chameleon: A Data-Efficient Generalist for Dense Visual Prediction in the Wild","arxiv_id":"2404.18459","date":"2024-04-29","proceeding":null,"authors":["Donggyun Kim","Seongwoong Cho","Semin Kim","Chong Luo","Seunghoon Hong"],"abstract":"Large language models have evolved data-efficient generalists, benefiting from the universal language interface and large-scale pre-training. However, constructing a data-efficient generalist for dense visual prediction presents a distinct challenge due to the variation in label structures across different tasks. Consequently, generalization to unseen dense prediction tasks in the low-data regime is not straightforward and has received less attention from previous vision generalists. In this study, we explore a universal model that can flexibly adapt to unseen dense label structures with a few examples, enabling it to serve as a data-efficient vision generalist in diverse real-world scenarios. To this end, we base our method on a powerful meta-learning framework and explore several axes to improve its performance and versatility for real-world problems, such as flexible adaptation mechanisms and scalability. We evaluate our model across a spectrum of unseen real-world scenarios where low-shot learning is desirable, including video, 3D, medical, biological, and user-interactive tasks. Equipped with a generic architecture and an effective adaptation mechanism, our model flexibly adapts to all of these tasks with at most 50 labeled images, showcasing a significant advancement over existing data-efficient generalist approaches. Codes are available at https://github.com/GitGyun/chameleon.","url_abs":"https://arxiv.org/abs/2404.18459v3","url_pdf":"https://arxiv.org/pdf/2404.18459v3.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":"chameleon-a-data-efficient-generalist-for","repo_url":"https://github.com/gitgyun/chameleon","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.18459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18459"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gitgyun/chameleon","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":"02a0579731cda8c1","entry":"linear_sample","repo":"gitgyun/chameleon","repo_kind":"official","path":"dataset/augmentation.py","file_url":"https://github.com/gitgyun/chameleon/blob/HEAD/dataset/augmentation.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":"02a0579731cda8c1"}},{"code_sha256_prefix":"98a7bede28cc1c47","entry":"log_sample","repo":"gitgyun/chameleon","repo_kind":"official","path":"dataset/augmentation.py","file_url":"https://github.com/gitgyun/chameleon/blob/HEAD/dataset/augmentation.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":"98a7bede28cc1c47"}},{"code_sha256_prefix":"f1aba098ff5cbc05","entry":"normalize","repo":"gitgyun/chameleon","repo_kind":"official","path":"dataset/augmentation.py","file_url":"https://github.com/gitgyun/chameleon/blob/HEAD/dataset/augmentation.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":"f1aba098ff5cbc05"}},{"code_sha256_prefix":"1a9f1b3ff0f40a80","entry":"spatial_softmax_loss","repo":"gitgyun/chameleon","repo_kind":"official","path":"train/loss.py","file_url":"https://github.com/gitgyun/chameleon/blob/HEAD/train/loss.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":"1a9f1b3ff0f40a80"}},{"code_sha256_prefix":"056b10a025a6480e","entry":"spatio_channel_softmax_loss","repo":"gitgyun/chameleon","repo_kind":"official","path":"train/loss.py","file_url":"https://github.com/gitgyun/chameleon/blob/HEAD/train/loss.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":"056b10a025a6480e"}},{"code_sha256_prefix":"c0ed6e00d7d1220d","entry":"parse_args","repo":"gitgyun/chameleon","repo_kind":"official","path":"args.py","file_url":"https://github.com/gitgyun/chameleon/blob/HEAD/args.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":"c0ed6e00d7d1220d"}},{"code_sha256_prefix":"0d5ccf3e418960d3","entry":"str2bool","repo":"gitgyun/chameleon","repo_kind":"official","path":"args.py","file_url":"https://github.com/gitgyun/chameleon/blob/HEAD/args.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":"0d5ccf3e418960d3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}