{"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/contrastive-learning-with-stronger-1","title":"Contrastive Learning with Stronger Augmentations","arxiv_id":"2104.07713","date":"2021-04-15","proceeding":null,"authors":["Xiao Wang","Guo-Jun Qi"],"abstract":"Representation learning has significantly been developed with the advance of contrastive learning methods. Most of those methods have benefited from various data augmentations that are carefully designated to maintain their identities so that the images transformed from the same instance can still be retrieved. However, those carefully designed transformations limited us to further explore the novel patterns exposed by other transformations. Meanwhile, as found in our experiments, the strong augmentations distorted the images' structures, resulting in difficult retrieval. Thus, we propose a general framework called Contrastive Learning with Stronger Augmentations~(CLSA) to complement current contrastive learning approaches. Here, the distribution divergence between the weakly and strongly augmented images over the representation bank is adopted to supervise the retrieval of strongly augmented queries from a pool of instances. Experiments on the ImageNet dataset and downstream datasets showed the information from the strongly augmented images can significantly boost the performance. For example, CLSA achieves top-1 accuracy of 76.2% on ImageNet with a standard ResNet-50 architecture with a single-layer classifier fine-tuned, which is almost the same level as 76.5% of supervised results. The code and pre-trained models are available in https://github.com/maple-research-lab/CLSA.","url_abs":"https://arxiv.org/abs/2104.07713v2","url_pdf":"https://arxiv.org/pdf/2104.07713v2.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":"contrastive-learning-with-stronger-1","repo_url":"https://github.com/maple-research-lab/CLSA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.07713","atlas_url":"https://app.syntology.ai/?focus=2104.07713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07713"}},"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/maple-research-lab/CLSA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":5},"by_repo_kind":{"official":{"samples":8,"ran":3,"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":"c6e7c3451c85404f","entry":"AutoContrast","repo":"maple-research-lab/CLSA","repo_kind":"official","path":"data_processing/RandAugment.py","file_url":"https://github.com/maple-research-lab/CLSA/blob/HEAD/data_processing/RandAugment.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6e7c3451c85404f"}},{"code_sha256_prefix":"0d1a8d6ce2015fc7","entry":"Brightness","repo":"maple-research-lab/CLSA","repo_kind":"official","path":"data_processing/RandAugment.py","file_url":"https://github.com/maple-research-lab/CLSA/blob/HEAD/data_processing/RandAugment.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d1a8d6ce2015fc7"}},{"code_sha256_prefix":"32cb3f5760fa593e","entry":"Color","repo":"maple-research-lab/CLSA","repo_kind":"official","path":"data_processing/RandAugment.py","file_url":"https://github.com/maple-research-lab/CLSA/blob/HEAD/data_processing/RandAugment.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32cb3f5760fa593e"}},{"code_sha256_prefix":"32f3f48791cdc94e","entry":"Config_Environment","repo":"maple-research-lab/CLSA","repo_kind":"official","path":"ops/Config_Envrionment.py","file_url":"https://github.com/maple-research-lab/CLSA/blob/HEAD/ops/Config_Envrionment.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":"32f3f48791cdc94e"}},{"code_sha256_prefix":"73cecca9f3575f09","entry":"concat_all_gather","repo":"maple-research-lab/CLSA","repo_kind":"official","path":"model/CLSA.py","file_url":"https://github.com/maple-research-lab/CLSA/blob/HEAD/model/CLSA.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":"73cecca9f3575f09"}},{"code_sha256_prefix":"c756f0e42368feee","entry":"encode_labels","repo":"maple-research-lab/CLSA","repo_kind":"official","path":"VOC_CLF/utils.py","file_url":"https://github.com/maple-research-lab/CLSA/blob/HEAD/VOC_CLF/utils.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":"c756f0e42368feee"}},{"code_sha256_prefix":"d5de38f848a793c8","entry":"get_categories","repo":"maple-research-lab/CLSA","repo_kind":"official","path":"VOC_CLF/utils.py","file_url":"https://github.com/maple-research-lab/CLSA/blob/HEAD/VOC_CLF/utils.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":"d5de38f848a793c8"}},{"code_sha256_prefix":"58dfc834a15b4a9a","entry":"get_nrows","repo":"maple-research-lab/CLSA","repo_kind":"official","path":"VOC_CLF/utils.py","file_url":"https://github.com/maple-research-lab/CLSA/blob/HEAD/VOC_CLF/utils.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":"58dfc834a15b4a9a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}