{"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/three-guidelines-you-should-know-for","title":"Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning","arxiv_id":"2303.06870","date":"2023-03-13","proceeding":"CVPR 2023 1","authors":["Yun-Hao Cao","Peiqin Sun","Shuchang Zhou"],"abstract":"We propose universally slimmable self-supervised learning (dubbed as US3L) to achieve better accuracy-efficiency trade-offs for deploying self-supervised models across different devices. We observe that direct adaptation of self-supervised learning (SSL) to universally slimmable networks misbehaves as the training process frequently collapses. We then discover that temporal consistent guidance is the key to the success of SSL for universally slimmable networks, and we propose three guidelines for the loss design to ensure this temporal consistency from a unified gradient perspective. Moreover, we propose dynamic sampling and group regularization strategies to simultaneously improve training efficiency and accuracy. Our US3L method has been empirically validated on both convolutional neural networks and vision transformers. With only once training and one copy of weights, our method outperforms various state-of-the-art methods (individually trained or not) on benchmarks including recognition, object detection and instance segmentation. Our code is available at https://github.com/megvii-research/US3L-CVPR2023.","url_abs":"https://arxiv.org/abs/2303.06870v1","url_pdf":"https://arxiv.org/pdf/2303.06870v1.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":"three-guidelines-you-should-know-for","repo_url":"https://github.com/megvii-research/us3l-cvpr2023","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.06870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06870"}},"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/megvii-research/us3l-cvpr2023","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":4,"ran_honours":1,"unverified":5},"by_repo_kind":{"official":{"samples":11,"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":"131a82fd65128218","entry":"accuracy","repo":"megvii-research/us3l-cvpr2023","repo_kind":"official","path":"ViT_experiments/main_lincls_ddp.py","file_url":"https://github.com/megvii-research/us3l-cvpr2023/blob/HEAD/ViT_experiments/main_lincls_ddp.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"131a82fd65128218"}},{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"megvii-research/us3l-cvpr2023","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/megvii-research/us3l-cvpr2023/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/us3l-cvpr2023","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/megvii-research/us3l-cvpr2023/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":"a0131fb70c267a9e","entry":"conv_1x1_bn","repo":"megvii-research/us3l-cvpr2023","repo_kind":"official","path":"models/mobilenetv2.py","file_url":"https://github.com/megvii-research/us3l-cvpr2023/blob/HEAD/models/mobilenetv2.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":"a0131fb70c267a9e"}},{"code_sha256_prefix":"e087cbfa1e53486d","entry":"conv_bn","repo":"megvii-research/us3l-cvpr2023","repo_kind":"official","path":"models/mobilenetv2.py","file_url":"https://github.com/megvii-research/us3l-cvpr2023/blob/HEAD/models/mobilenetv2.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":"e087cbfa1e53486d"}},{"code_sha256_prefix":"5c22680084c0ea6f","entry":"validate","repo":"megvii-research/us3l-cvpr2023","repo_kind":"official","path":"ViT_experiments/main_lincls_ddp.py","file_url":"https://github.com/megvii-research/us3l-cvpr2023/blob/HEAD/ViT_experiments/main_lincls_ddp.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c22680084c0ea6f"}},{"code_sha256_prefix":"bec58d24a35b5474","entry":"get_config","repo":"megvii-research/us3l-cvpr2023","repo_kind":"official","path":"config.py","file_url":"https://github.com/megvii-research/us3l-cvpr2023/blob/HEAD/config.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":"bec58d24a35b5474"}},{"code_sha256_prefix":"d5dc1a04345a8ec5","entry":"get_state_dict","repo":"megvii-research/us3l-cvpr2023","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/megvii-research/us3l-cvpr2023/blob/HEAD/models/utils.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":"d5dc1a04345a8ec5"}},{"code_sha256_prefix":"31442fa117f34eda","entry":"imdecode","repo":"megvii-research/us3l-cvpr2023","repo_kind":"official","path":"ViT_experiments/datasets/imagenet.py","file_url":"https://github.com/megvii-research/us3l-cvpr2023/blob/HEAD/ViT_experiments/datasets/imagenet.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":"31442fa117f34eda"}},{"code_sha256_prefix":"b7f1311fe16c1c45","entry":"mobilenetv2","repo":"megvii-research/us3l-cvpr2023","repo_kind":"official","path":"models/mobilenetv2.py","file_url":"https://github.com/megvii-research/us3l-cvpr2023/blob/HEAD/models/mobilenetv2.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":"b7f1311fe16c1c45"}},{"code_sha256_prefix":"39fa93771a61fe5b","entry":"update_config","repo":"megvii-research/us3l-cvpr2023","repo_kind":"official","path":"config.py","file_url":"https://github.com/megvii-research/us3l-cvpr2023/blob/HEAD/config.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":"39fa93771a61fe5b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}