{"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/how-well-do-self-supervised-models-transfer","title":"How Well Do Self-Supervised Models Transfer?","arxiv_id":"2011.13377","date":"2020-11-26","proceeding":"CVPR 2021 1","authors":["Linus Ericsson","Henry Gouk","Timothy M. Hospedales"],"abstract":"Self-supervised visual representation learning has seen huge progress recently, but no large scale evaluation has compared the many models now available. We evaluate the transfer performance of 13 top self-supervised models on 40 downstream tasks, including many-shot and few-shot recognition, object detection, and dense prediction. We compare their performance to a supervised baseline and show that on most tasks the best self-supervised models outperform supervision, confirming the recently observed trend in the literature. We find ImageNet Top-1 accuracy to be highly correlated with transfer to many-shot recognition, but increasingly less so for few-shot, object detection and dense prediction. No single self-supervised method dominates overall, suggesting that universal pre-training is still unsolved. Our analysis of features suggests that top self-supervised learners fail to preserve colour information as well as supervised alternatives, but tend to induce better classifier calibration, and less attentive overfitting than supervised learners.","url_abs":"https://arxiv.org/abs/2011.13377v2","url_pdf":"https://arxiv.org/pdf/2011.13377v2.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":"how-well-do-self-supervised-models-transfer","repo_url":"https://github.com/linusericsson/ssl-transfer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classifier-calibration","task_name":"Classifier calibration"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"fine-grained-image-recognition","task_name":"Fine-Grained Image Recognition"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"surface-normals-estimation","task_name":"Surface Normals Estimation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"byol","method_name":"BYOL"},{"method_slug":"moco","method_name":"MoCo"},{"method_slug":"moco-v2","method_name":"MoCo v2"},{"method_slug":"npid","method_name":"NPID"},{"method_slug":"pirl","method_name":"PIRL"},{"method_slug":"simclr","method_name":"SimCLR"},{"method_slug":"swav","method_name":"SwAV"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2011.13377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.13377"}},"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/linusericsson/ssl-transfer","reach":null}],"summary":{"ran_fixture":2,"ran_draft_wrong":1,"ran_honours":1,"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":"e628a3f24dbdf568","entry":"count_acc","repo":"linusericsson/ssl-transfer","repo_kind":"official","path":"finetune.py","file_url":"https://github.com/linusericsson/ssl-transfer/blob/HEAD/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e628a3f24dbdf568"}},{"code_sha256_prefix":"4dd319c45d372246","entry":"euclidean_dist","repo":"linusericsson/ssl-transfer","repo_kind":"official","path":"few_shot.py","file_url":"https://github.com/linusericsson/ssl-transfer/blob/HEAD/few_shot.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4dd319c45d372246"}},{"code_sha256_prefix":"fb52994d0ed2666d","entry":"voc_ap","repo":"linusericsson/ssl-transfer","repo_kind":"official","path":"linear.py","file_url":"https://github.com/linusericsson/ssl-transfer/blob/HEAD/linear.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb52994d0ed2666d"}},{"code_sha256_prefix":"da6e06cd5690114a","entry":"voc_eval_cls","repo":"linusericsson/ssl-transfer","repo_kind":"official","path":"linear.py","file_url":"https://github.com/linusericsson/ssl-transfer/blob/HEAD/linear.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da6e06cd5690114a"}},{"code_sha256_prefix":"9f379d81ff970e3a","entry":"get_dataset","repo":"linusericsson/ssl-transfer","repo_kind":"official","path":"linear.py","file_url":"https://github.com/linusericsson/ssl-transfer/blob/HEAD/linear.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":"9f379d81ff970e3a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}