{"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/revisiting-the-critical-factors-of","title":"Revisiting the Critical Factors of Augmentation-Invariant Representation Learning","arxiv_id":"2208.00275","date":"2022-07-30","proceeding":null,"authors":["Junqiang Huang","Xiangwen Kong","Xiangyu Zhang"],"abstract":"We focus on better understanding the critical factors of augmentation-invariant representation learning. We revisit MoCo v2 and BYOL and try to prove the authenticity of the following assumption: different frameworks bring about representations of different characteristics even with the same pretext task. We establish the first benchmark for fair comparisons between MoCo v2 and BYOL, and observe: (i) sophisticated model configurations enable better adaptation to pre-training dataset; (ii) mismatched optimization strategies of pre-training and fine-tuning hinder model from achieving competitive transfer performances. Given the fair benchmark, we make further investigation and find asymmetry of network structure endows contrastive frameworks to work well under the linear evaluation protocol, while may hurt the transfer performances on long-tailed classification tasks. Moreover, negative samples do not make models more sensible to the choice of data augmentations, nor does the asymmetric network structure. We believe our findings provide useful information for future work.","url_abs":"https://arxiv.org/abs/2208.00275v1","url_pdf":"https://arxiv.org/pdf/2208.00275v1.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":"revisiting-the-critical-factors-of","repo_url":"https://github.com/megvii-research/revisitairl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"linear-evaluation","task_name":"Linear evaluation"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"byol","method_name":"BYOL"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"infonce","method_name":"InfoNCE"},{"method_slug":"moco","method_name":"MoCo"},{"method_slug":"moco-v2","method_name":"MoCo v2"},{"method_slug":"random-gaussian-blur","method_name":"Random Gaussian Blur"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.00275","atlas_url":"https://app.syntology.ai/?focus=2208.00275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.00275"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/megvii-research/revisitairl","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":"e0c91cd1160e94e2","entry":"build_optimizer","repo":"megvii-research/revisitairl","repo_kind":"official","path":"linear_eval.py","file_url":"https://github.com/megvii-research/revisitairl/blob/HEAD/linear_eval.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e0c91cd1160e94e2"}},{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"megvii-research/revisitairl","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/megvii-research/revisitairl/blob/HEAD/models/resnet.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"megvii-research/revisitairl","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/megvii-research/revisitairl/blob/HEAD/models/resnet.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"160bb14bd76201b4"}},{"code_sha256_prefix":"8dc744ee7b17884d","entry":"load_weights","repo":"megvii-research/revisitairl","repo_kind":"official","path":"linear_eval.py","file_url":"https://github.com/megvii-research/revisitairl/blob/HEAD/linear_eval.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8dc744ee7b17884d"}},{"code_sha256_prefix":"4ae629012e034bbc","entry":"build_model","repo":"megvii-research/revisitairl","repo_kind":"official","path":"linear_eval.py","file_url":"https://github.com/megvii-research/revisitairl/blob/HEAD/linear_eval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4ae629012e034bbc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}