{"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/surprising-effectiveness-of-few-image","title":"A critical analysis of self-supervision, or what we can learn from a single image","arxiv_id":"1904.13132","date":"2019-04-30","proceeding":"ICLR 2020 1","authors":["Yuki M. Asano","Christian Rupprecht","Andrea Vedaldi"],"abstract":"We look critically at popular self-supervision techniques for learning deep convolutional neural networks without manual labels. We show that three different and representative methods, BiGAN, RotNet and DeepCluster, can learn the first few layers of a convolutional network from a single image as well as using millions of images and manual labels, provided that strong data augmentation is used. However, for deeper layers the gap with manual supervision cannot be closed even if millions of unlabelled images are used for training. We conclude that: (1) the weights of the early layers of deep networks contain limited information about the statistics of natural images, that (2) such low-level statistics can be learned through self-supervision just as well as through strong supervision, and that (3) the low-level statistics can be captured via synthetic transformations instead of using a large image dataset.","url_abs":"https://arxiv.org/abs/1904.13132v3","url_pdf":"https://arxiv.org/pdf/1904.13132v3.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":"surprising-effectiveness-of-few-image","repo_url":"https://github.com/yukimasano/linear-probes","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"surprising-effectiveness-of-few-image","repo_url":"https://github.com/yukimasano/single_img_pretraining","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"bigan","method_name":"BiGAN"},{"method_slug":"deepcluster","method_name":"DeepCluster"},{"method_slug":"k-means-clustering","method_name":"k-Means Clustering"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.13132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.13132"}},"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/yukimasano/linear-probes","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yukimasano/single_img_pretraining","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"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":"156efde5a5906f82","entry":"get_mono_data_loader","repo":"yukimasano/single_img_pretraining","repo_kind":"listed","path":"make_dataset_single.py","file_url":"https://github.com/yukimasano/single_img_pretraining/blob/HEAD/make_dataset_single.py","link_basis":"harvester_set","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":"156efde5a5906f82"}},{"code_sha256_prefix":"ec62fc8046161931","entry":"make_","repo":"yukimasano/single_img_pretraining","repo_kind":"listed","path":"make_dataset_single.py","file_url":"https://github.com/yukimasano/single_img_pretraining/blob/HEAD/make_dataset_single.py","link_basis":"harvester_set","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":"ec62fc8046161931"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}