{"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/augmentation-aware-self-supervised-learning","title":"Augmentation-aware Self-supervised Learning with Conditioned Projector","arxiv_id":"2306.06082","date":"2023-05-31","proceeding":null,"authors":["Marcin Przewięźlikowski","Mateusz Pyla","Bartosz Zieliński","Bartłomiej Twardowski","Jacek Tabor","Marek Śmieja"],"abstract":"Self-supervised learning (SSL) is a powerful technique for learning from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo can reach quality on par with supervised approaches. However, this invariance may be detrimental for solving downstream tasks that depend on traits affected by augmentations used during pretraining, such as color. In this paper, we propose to foster sensitivity to such characteristics in the representation space by modifying the projector network, a common component of self-supervised architectures. Specifically, we supplement the projector with information about augmentations applied to images. For the projector to take advantage of this auxiliary conditioning when solving the SSL task, the feature extractor learns to preserve the augmentation information in its representations. Our approach, coined Conditional Augmentation-aware Self-supervised Learning (CASSLE), is directly applicable to typical joint-embedding SSL methods regardless of their objective functions. Moreover, it does not require major changes in the network architecture or prior knowledge of downstream tasks. In addition to an analysis of sensitivity towards different data augmentations, we conduct a series of experiments, which show that CASSLE improves over various SSL methods, reaching state-of-the-art performance in multiple downstream tasks.","url_abs":"https://arxiv.org/abs/2306.06082v4","url_pdf":"https://arxiv.org/pdf/2306.06082v4.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":"augmentation-aware-self-supervised-learning","repo_url":"https://github.com/gmum/cassle","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"sensitivity","task_name":"Sensitivity"}],"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":"colorjitter","method_name":"ColorJitter"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"infonce","method_name":"InfoNCE"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"moco","method_name":"MoCo"},{"method_slug":"nt-xent","method_name":"NT-Xent"},{"method_slug":"random-gaussian-blur","method_name":"Random Gaussian Blur"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"simclr","method_name":"SimCLR"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.06082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.06082"}},"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/gmum/cassle","reach":null}],"summary":{"ran_draft_wrong":4,"unverified":5},"by_repo_kind":{"official":{"samples":9,"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":9,"samples":[{"code_sha256_prefix":"cc6398d7c1e8fe63","entry":"build_step","repo":"gmum/cassle","repo_kind":"official","path":"transfer_linear_eval.py","file_url":"https://github.com/gmum/cassle/blob/HEAD/transfer_linear_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cc6398d7c1e8fe63"}},{"code_sha256_prefix":"a0a460245ff72f14","entry":"l1_criterion_fn","repo":"gmum/cassle","repo_kind":"official","path":"transfer_linear_eval.py","file_url":"https://github.com/gmum/cassle/blob/HEAD/transfer_linear_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a0a460245ff72f14"}},{"code_sha256_prefix":"87b60ab57abad47e","entry":"load_mlp","repo":"gmum/cassle","repo_kind":"official","path":"cond_utils.py","file_url":"https://github.com/gmum/cassle/blob/HEAD/cond_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"87b60ab57abad47e"}},{"code_sha256_prefix":"1706ee2e8470327b","entry":"r2_fn","repo":"gmum/cassle","repo_kind":"official","path":"transfer_linear_eval.py","file_url":"https://github.com/gmum/cassle/blob/HEAD/transfer_linear_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1706ee2e8470327b"}},{"code_sha256_prefix":"ecbd1316ed923a2b","entry":"AUG_HN_TYPES","repo":"gmum/cassle","repo_kind":"official","path":"cond_utils.py","file_url":"https://github.com/gmum/cassle/blob/HEAD/cond_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ecbd1316ed923a2b"}},{"code_sha256_prefix":"6a90c8e144d2c4b0","entry":"AUG_INJECTION_TYPES","repo":"gmum/cassle","repo_kind":"official","path":"cond_utils.py","file_url":"https://github.com/gmum/cassle/blob/HEAD/cond_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6a90c8e144d2c4b0"}},{"code_sha256_prefix":"a64b4fc2977ee2b5","entry":"AUG_STRATEGY","repo":"gmum/cassle","repo_kind":"official","path":"cond_utils.py","file_url":"https://github.com/gmum/cassle/blob/HEAD/cond_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a64b4fc2977ee2b5"}},{"code_sha256_prefix":"465eeb270d5769bb","entry":"AugProjector","repo":"gmum/cassle","repo_kind":"official","path":"cond_utils.py","file_url":"https://github.com/gmum/cassle/blob/HEAD/cond_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"465eeb270d5769bb"}},{"code_sha256_prefix":"2a8385c904c3909e","entry":"reset_parameters","repo":"gmum/cassle","repo_kind":"official","path":"cond_utils.py","file_url":"https://github.com/gmum/cassle/blob/HEAD/cond_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2a8385c904c3909e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}