{"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/active-learning-by-feature-mixing","title":"Active Learning by Feature Mixing","arxiv_id":"2203.07034","date":"2022-03-14","proceeding":"CVPR 2022 1","authors":["Amin Parvaneh","Ehsan Abbasnejad","Damien Teney","Reza Haffari","Anton Van Den Hengel","Javen Qinfeng Shi"],"abstract":"The promise of active learning (AL) is to reduce labelling costs by selecting the most valuable examples to annotate from a pool of unlabelled data. Identifying these examples is especially challenging with high-dimensional data (e.g. images, videos) and in low-data regimes. In this paper, we propose a novel method for batch AL called ALFA-Mix. We identify unlabelled instances with sufficiently-distinct features by seeking inconsistencies in predictions resulting from interventions on their representations. We construct interpolations between representations of labelled and unlabelled instances then examine the predicted labels. We show that inconsistencies in these predictions help discovering features that the model is unable to recognise in the unlabelled instances. We derive an efficient implementation based on a closed-form solution to the optimal interpolation causing changes in predictions. Our method outperforms all recent AL approaches in 30 different settings on 12 benchmarks of images, videos, and non-visual data. The improvements are especially significant in low-data regimes and on self-trained vision transformers, where ALFA-Mix outperforms the state-of-the-art in 59% and 43% of the experiments respectively.","url_abs":"https://arxiv.org/abs/2203.07034v1","url_pdf":"https://arxiv.org/pdf/2203.07034v1.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":"active-learning-by-feature-mixing","repo_url":"https://github.com/aminparvaneh/alpha_mix_active_learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"active-learning-by-feature-mixing","repo_url":"https://github.com/dsba-lab/openal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"active-learning-by-feature-mixing","repo_url":"https://github.com/duojun-huang/diana-cvpr2023","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"active-learning-by-feature-mixing","repo_url":"https://github.com/Mind23-2/MindCode-157","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.07034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07034"}},"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/duojun-huang/diana-cvpr2023","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dsba-lab/openal","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aminparvaneh/alpha_mix_active_learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-157","reach":{"status":"ok"}}],"summary":{"ran":6,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1},"listed":{"samples":6,"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":2,"samples":[{"code_sha256_prefix":"e75f4ac8794a8b1c","entry":"AlphaMixSampling","repo":"dsba-lab/openal","repo_kind":"listed","path":"query_strategies/featmix_sampling.py","file_url":"https://github.com/dsba-lab/openal/blob/HEAD/query_strategies/featmix_sampling.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":"e75f4ac8794a8b1c"}},{"code_sha256_prefix":"bf475d60bd681390","entry":"Strategy","repo":"dsba-lab/openal","repo_kind":"listed","path":"query_strategies/featmix_sampling.py","file_url":"https://github.com/dsba-lab/openal/blob/HEAD/query_strategies/featmix_sampling.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":"bf475d60bd681390"}},{"code_sha256_prefix":"2661daeb22d41bb0","entry":"Strategy","repo":"aminparvaneh/alpha_mix_active_learning","repo_kind":"official","path":"query_strategies/alpha_mix_sampling.py","file_url":"https://github.com/aminparvaneh/alpha_mix_active_learning/blob/HEAD/query_strategies/alpha_mix_sampling.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":"2661daeb22d41bb0"}},{"code_sha256_prefix":"c15a37c34d489f09","entry":"SubsetSequentialSampler","repo":"dsba-lab/openal","repo_kind":"listed","path":"query_strategies/featmix_sampling.py","file_url":"https://github.com/dsba-lab/openal/blob/HEAD/query_strategies/featmix_sampling.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":"c15a37c34d489f09"}},{"code_sha256_prefix":"c3df65aa7a3cf216","entry":"SubsetWeightedRandomSampler","repo":"dsba-lab/openal","repo_kind":"listed","path":"query_strategies/featmix_sampling.py","file_url":"https://github.com/dsba-lab/openal/blob/HEAD/query_strategies/featmix_sampling.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":"c3df65aa7a3cf216"}},{"code_sha256_prefix":"2e91b401d6cc9f05","entry":"TrainIterableDataset","repo":"dsba-lab/openal","repo_kind":"listed","path":"query_strategies/featmix_sampling.py","file_url":"https://github.com/dsba-lab/openal/blob/HEAD/query_strategies/featmix_sampling.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":"2e91b401d6cc9f05"}},{"code_sha256_prefix":"52d51edd564dc57a","entry":"get_target_from_dataset","repo":"dsba-lab/openal","repo_kind":"listed","path":"query_strategies/featmix_sampling.py","file_url":"https://github.com/dsba-lab/openal/blob/HEAD/query_strategies/featmix_sampling.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"52d51edd564dc57a"}},{"code_sha256_prefix":"6b8bd51846dfad76","entry":"AlphaMixSampling","repo":"aminparvaneh/alpha_mix_active_learning","repo_kind":"official","path":"query_strategies/alpha_mix_sampling.py","file_url":"https://github.com/aminparvaneh/alpha_mix_active_learning/blob/HEAD/query_strategies/alpha_mix_sampling.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":"6b8bd51846dfad76"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}