{"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/on-pretraining-data-diversity-for-self","title":"On Pretraining Data Diversity for Self-Supervised Learning","arxiv_id":"2403.13808","date":"2024-03-20","proceeding":null,"authors":["Hasan Abed Al Kader Hammoud","Tuhin Das","Fabio Pizzati","Philip Torr","Adel Bibi","Bernard Ghanem"],"abstract":"We explore the impact of training with more diverse datasets, characterized by the number of unique samples, on the performance of self-supervised learning (SSL) under a fixed computational budget. Our findings consistently demonstrate that increasing pretraining data diversity enhances SSL performance, albeit only when the distribution distance to the downstream data is minimal. Notably, even with an exceptionally large pretraining data diversity achieved through methods like web crawling or diffusion-generated data, among other ways, the distribution shift remains a challenge. Our experiments are comprehensive with seven SSL methods using large-scale datasets such as ImageNet and YFCC100M amounting to over 200 GPU days. Code and trained models are available at https://github.com/hammoudhasan/DiversitySSL","url_abs":"https://arxiv.org/abs/2403.13808v3","url_pdf":"https://arxiv.org/pdf/2403.13808v3.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":"on-pretraining-data-diversity-for-self","repo_url":"https://github.com/hammoudhasan/diversityssl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.13808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13808"}},"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/hammoudhasan/diversityssl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":"132a949a804eb81e","entry":"barlow_loss_func","repo":"hammoudhasan/diversityssl","repo_kind":"official","path":"solo/losses/barlow.py","file_url":"https://github.com/hammoudhasan/diversityssl/blob/HEAD/solo/losses/barlow.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":"132a949a804eb81e"}},{"code_sha256_prefix":"273532e06cb3967e","entry":"byol_loss_func","repo":"hammoudhasan/diversityssl","repo_kind":"official","path":"solo/losses/byol.py","file_url":"https://github.com/hammoudhasan/diversityssl/blob/HEAD/solo/losses/byol.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"273532e06cb3967e"}},{"code_sha256_prefix":"8916e0f98b777300","entry":"extract_features","repo":"hammoudhasan/diversityssl","repo_kind":"official","path":"main_knn.py","file_url":"https://github.com/hammoudhasan/diversityssl/blob/HEAD/main_knn.py","link_basis":"first_harvest_node","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":"8916e0f98b777300"}},{"code_sha256_prefix":"a07d9a7525702b80","entry":"mae_loss_func","repo":"hammoudhasan/diversityssl","repo_kind":"official","path":"solo/losses/mae.py","file_url":"https://github.com/hammoudhasan/diversityssl/blob/HEAD/solo/losses/mae.py","link_basis":"first_harvest_node","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":"a07d9a7525702b80"}},{"code_sha256_prefix":"4dd7c3cff0150cb9","entry":"mocov2plus_loss_func","repo":"hammoudhasan/diversityssl","repo_kind":"official","path":"solo/losses/mocov2plus.py","file_url":"https://github.com/hammoudhasan/diversityssl/blob/HEAD/solo/losses/mocov2plus.py","link_basis":"plan_row","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":"4dd7c3cff0150cb9"}},{"code_sha256_prefix":"3e6a557bf1ad83d9","entry":"patchify","repo":"hammoudhasan/diversityssl","repo_kind":"official","path":"solo/losses/mae.py","file_url":"https://github.com/hammoudhasan/diversityssl/blob/HEAD/solo/losses/mae.py","link_basis":"first_harvest_node","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":"3e6a557bf1ad83d9"}},{"code_sha256_prefix":"ce432f2e9653c7a3","entry":"deepclusterv2_loss_func","repo":"hammoudhasan/diversityssl","repo_kind":"official","path":"solo/losses/deepclusterv2.py","file_url":"https://github.com/hammoudhasan/diversityssl/blob/HEAD/solo/losses/deepclusterv2.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":"ce432f2e9653c7a3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}