{"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/pushing-the-limits-of-self-supervised-resnets","title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","arxiv_id":"2201.05119","date":"2022-01-13","proceeding":null,"authors":["Nenad Tomasev","Ioana Bica","Brian McWilliams","Lars Buesing","Razvan Pascanu","Charles Blundell","Jovana Mitrovic"],"abstract":"Despite recent progress made by self-supervised methods in representation learning with residual networks, they still underperform supervised learning on the ImageNet classification benchmark, limiting their applicability in performance-critical settings. Building on prior theoretical insights from ReLIC [Mitrovic et al., 2021], we include additional inductive biases into self-supervised learning. We propose a new self-supervised representation learning method, ReLICv2, which combines an explicit invariance loss with a contrastive objective over a varied set of appropriately constructed data views to avoid learning spurious correlations and obtain more informative representations. ReLICv2 achieves $77.1\\%$ top-$1$ accuracy on ImageNet under linear evaluation on a ResNet50, thus improving the previous state-of-the-art by absolute $+1.5\\%$; on larger ResNet models, ReLICv2 achieves up to $80.6\\%$ outperforming previous self-supervised approaches with margins up to $+2.3\\%$. Most notably, ReLICv2 is the first unsupervised representation learning method to consistently outperform the supervised baseline in a like-for-like comparison over a range of ResNet architectures. Using ReLICv2, we also learn more robust and transferable representations that generalize better out-of-distribution than previous work, both on image classification and semantic segmentation. Finally, we show that despite using ResNet encoders, ReLICv2 is comparable to state-of-the-art self-supervised vision transformers.","url_abs":"https://arxiv.org/abs/2201.05119v2","url_pdf":"https://arxiv.org/pdf/2201.05119v2.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":"pushing-the-limits-of-self-supervised-resnets","repo_url":"https://github.com/google-deepmind/relicv2","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"linear-evaluation","task_name":"Linear evaluation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relic","method_name":"ReLIC"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"RELICv2","rank_in_archive_order":79,"of":106,"metrics":{"Top-1 Accuracy":"25.9"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"RELIC","rank_in_archive_order":84,"of":106,"metrics":{"Top-1 Accuracy":"23.8"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"BYOL","rank_in_archive_order":85,"of":106,"metrics":{"Top-1 Accuracy":"23"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"SimCLR","rank_in_archive_order":99,"of":106,"metrics":{"Top-1 Accuracy":"14.6"},"uses_additional_data":true},{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"ReLICv2 (ResNet-200 x2)","rank_in_archive_order":21,"of":144,"metrics":{"Number of Params":"250M","Top 1 Accuracy":"80.6%"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"ReLICv2 (ResNet200)","rank_in_archive_order":31,"of":144,"metrics":{"Number of Params":"63M","Top 1 Accuracy":"79.8%"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"ReLICv2 (ResNet-50 4x)","rank_in_archive_order":34,"of":144,"metrics":{"Number of Params":"375M","Top 1 Accuracy":"79.4%"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"ReLICv2 (ResNet152)","rank_in_archive_order":35,"of":144,"metrics":{"Number of Params":"58M","Top 1 Accuracy":"79.3%"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"ReLICv2 (ResNet-50 x2)","rank_in_archive_order":40,"of":144,"metrics":{"Number of Params":"94M","Top 1 Accuracy":"79%"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"ReLICv2 (ResNet101)","rank_in_archive_order":43,"of":144,"metrics":{"Number of Params":"44M","Top 1 Accuracy":"78.7%"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"ReLICv2 (ResNet-50)","rank_in_archive_order":55,"of":144,"metrics":{"Number of Params":"25M","Top 1 Accuracy":"77.1%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"ReLICv2","rank_in_archive_order":74,"of":99,"metrics":{"mIoU":"75.2"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"BYOL","rank_in_archive_order":77,"of":99,"metrics":{"mIoU":"74.6"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012-val","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"ReLICv2","rank_in_archive_order":14,"of":29,"metrics":{"mIoU":"77.9%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012-val","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"DetCon","rank_in_archive_order":17,"of":29,"metrics":{"mIoU":"77.3%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012-val","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"BYOL","rank_in_archive_order":20,"of":29,"metrics":{"mIoU":"75.7%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"RELICv2","rank_in_archive_order":41,"of":65,"metrics":{"Top 1 Accuracy":"58.1%","Top 5 Accuracy":"81.3"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"RELICv2 (ResNet-50)","rank_in_archive_order":38,"of":75,"metrics":{"Top 1 Accuracy":"72.4%","Top 5 Accuracy":"91.2%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.05119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05119"}},"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/google-deepmind/relicv2","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":14},"by_repo_kind":{"official":{"samples":14,"ran":0,"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":"9bc378261f9ad601","entry":"add_weight_decay","repo":"google-deepmind/relicv2","repo_kind":"official","path":"utils/optimizers.py","file_url":"https://github.com/google-deepmind/relicv2/blob/HEAD/utils/optimizers.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":"9bc378261f9ad601"}},{"code_sha256_prefix":"7cf26db115ac0335","entry":"exclude_bias_and_norm","repo":"google-deepmind/relicv2","repo_kind":"official","path":"utils/optimizers.py","file_url":"https://github.com/google-deepmind/relicv2/blob/HEAD/utils/optimizers.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":"7cf26db115ac0335"}},{"code_sha256_prefix":"56b9317b9ed66304","entry":"hsv_to_rgb","repo":"google-deepmind/relicv2","repo_kind":"official","path":"utils/augmentations.py","file_url":"https://github.com/google-deepmind/relicv2/blob/HEAD/utils/augmentations.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":"56b9317b9ed66304"}},{"code_sha256_prefix":"8df258170fa3cb79","entry":"l2_normalize","repo":"google-deepmind/relicv2","repo_kind":"official","path":"utils/helpers.py","file_url":"https://github.com/google-deepmind/relicv2/blob/HEAD/utils/helpers.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":"8df258170fa3cb79"}},{"code_sha256_prefix":"5e9e28416e760f15","entry":"learning_schedule","repo":"google-deepmind/relicv2","repo_kind":"official","path":"utils/schedules.py","file_url":"https://github.com/google-deepmind/relicv2/blob/HEAD/utils/schedules.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":"5e9e28416e760f15"}},{"code_sha256_prefix":"5b529484c13fcd15","entry":"load_checkpoint","repo":"google-deepmind/relicv2","repo_kind":"official","path":"utils/checkpointing.py","file_url":"https://github.com/google-deepmind/relicv2/blob/HEAD/utils/checkpointing.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":"5b529484c13fcd15"}},{"code_sha256_prefix":"9299bed7da61102a","entry":"normalize_images","repo":"google-deepmind/relicv2","repo_kind":"official","path":"utils/dataset.py","file_url":"https://github.com/google-deepmind/relicv2/blob/HEAD/utils/dataset.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":"9299bed7da61102a"}},{"code_sha256_prefix":"c14a511164946e31","entry":"postprocess","repo":"google-deepmind/relicv2","repo_kind":"official","path":"utils/augmentations.py","file_url":"https://github.com/google-deepmind/relicv2/blob/HEAD/utils/augmentations.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":"c14a511164946e31"}},{"code_sha256_prefix":"bf9bb14716c6dab9","entry":"rgb_to_hsv","repo":"google-deepmind/relicv2","repo_kind":"official","path":"utils/augmentations.py","file_url":"https://github.com/google-deepmind/relicv2/blob/HEAD/utils/augmentations.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":"bf9bb14716c6dab9"}},{"code_sha256_prefix":"79415fc4013fff5c","entry":"scale_by_lars","repo":"google-deepmind/relicv2","repo_kind":"official","path":"utils/optimizers.py","file_url":"https://github.com/google-deepmind/relicv2/blob/HEAD/utils/optimizers.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":"79415fc4013fff5c"}},{"code_sha256_prefix":"37ae8f08fc24a7d8","entry":"softmax_cross_entropy","repo":"google-deepmind/relicv2","repo_kind":"official","path":"utils/helpers.py","file_url":"https://github.com/google-deepmind/relicv2/blob/HEAD/utils/helpers.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":"37ae8f08fc24a7d8"}},{"code_sha256_prefix":"8c0e47e0bfa8f06f","entry":"target_ema","repo":"google-deepmind/relicv2","repo_kind":"official","path":"utils/schedules.py","file_url":"https://github.com/google-deepmind/relicv2/blob/HEAD/utils/schedules.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":"8c0e47e0bfa8f06f"}},{"code_sha256_prefix":"73ed5cd901b2ff52","entry":"topk_accuracy","repo":"google-deepmind/relicv2","repo_kind":"official","path":"utils/helpers.py","file_url":"https://github.com/google-deepmind/relicv2/blob/HEAD/utils/helpers.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":"73ed5cd901b2ff52"}},{"code_sha256_prefix":"301ebdfc332bbcc9","entry":"transpose_images","repo":"google-deepmind/relicv2","repo_kind":"official","path":"utils/dataset.py","file_url":"https://github.com/google-deepmind/relicv2/blob/HEAD/utils/dataset.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":"301ebdfc332bbcc9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}