{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/leveraging-background-augmentations-to","title":"Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations","arxiv_id":"2103.12719","date":"2021-03-23","proceeding":null,"authors":["Chaitanya K. Ryali","David J. Schwab","Ari S. Morcos"],"abstract":"Recent progress in self-supervised learning has demonstrated promising results in multiple visual tasks. An important ingredient in high-performing self-supervised methods is the use of data augmentation by training models to place different augmented views of the same image nearby in embedding space. However, commonly used augmentation pipelines treat images holistically, ignoring the semantic relevance of parts of an image-e.g. a subject vs. a background-which can lead to the learning of spurious correlations. Our work addresses this problem by investigating a class of simple, yet highly effective \"background augmentations\", which encourage models to focus on semantically-relevant content by discouraging them from focusing on image backgrounds. Through a systematic investigation, we show that background augmentations lead to substantial improvements in performance across a spectrum of state-of-the-art self-supervised methods (MoCo-v2, BYOL, SwAV) on a variety of tasks, e.g. $\\sim$+1-2% gains on ImageNet, enabling performance on par with the supervised baseline. Further, we find the improvement in limited-labels settings is even larger (up to 4.2%). Background augmentations also improve robustness to a number of distribution shifts, including natural adversarial examples, ImageNet-9, adversarial attacks, ImageNet-Renditions. We also make progress in completely unsupervised saliency detection, in the process of generating saliency masks used for background augmentations.","url_abs":"https://arxiv.org/abs/2103.12719v2","url_pdf":"https://arxiv.org/pdf/2103.12719v2.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":[],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"saliency-detection","task_name":"Saliency Detection"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"unsupervised-saliency-detection","task_name":"Unsupervised Saliency Detection"}],"methods":[{"method_slug":"byol","method_name":"BYOL"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"BYOL (BG_RM)","rank_in_archive_order":83,"of":106,"metrics":{"Top-1 Accuracy":"23.9"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"SwAV (BG_RM)","rank_in_archive_order":86,"of":106,"metrics":{"Top-1 Accuracy":"21.9"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"MoCo-v2 (BG_Swaps)","rank_in_archive_order":88,"of":106,"metrics":{"Top-1 Accuracy":"20.8"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.12719","atlas_url":"https://app.syntology.ai/?focus=2103.12719","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2103.12719"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2103.12719\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2103.12719"},"call":"get_concepts_for_paper(arxiv_id=\"2103.12719\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d3999fb7072a318192c19602c5e316daa2c31c77ab8cab5f8df1d5d007715718","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}