{"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/frossl-frobenius-norm-minimization-for-self","title":"FroSSL: Frobenius Norm Minimization for Efficient Multiview Self-Supervised Learning","arxiv_id":"2310.02903","date":"2023-10-04","proceeding":null,"authors":["Oscar Skean","Aayush Dhakal","Nathan Jacobs","Luis Gonzalo Sanchez Giraldo"],"abstract":"Self-supervised learning (SSL) is a popular paradigm for representation learning. Recent multiview methods can be classified as sample-contrastive, dimension-contrastive, or asymmetric network-based, with each family having its own approach to avoiding informational collapse. While these families converge to solutions of similar quality, it can be empirically shown that some methods are epoch-inefficient and require longer training to reach a target performance. Two main approaches to improving efficiency are covariance eigenvalue regularization and using more views. However, these two approaches are difficult to combine due to the computational complexity of computing eigenvalues. We present the objective function FroSSL which reconciles both approaches while avoiding eigendecomposition entirely. FroSSL works by minimizing covariance Frobenius norms to avoid collapse and minimizing mean-squared error to achieve augmentation invariance. We show that FroSSL reaches competitive accuracies more quickly than any other SSL method and provide theoretical and empirical support that this faster convergence is due to how FroSSL affects the eigenvalues of the embedding covariance matrices. We also show that FroSSL learns competitive representations on linear probe evaluation when used to train a ResNet-18 on several datasets, including STL-10, Tiny ImageNet, and ImageNet-100.","url_abs":"https://arxiv.org/abs/2310.02903v4","url_pdf":"https://arxiv.org/pdf/2310.02903v4.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":"frossl-frobenius-norm-minimization-for-self","repo_url":"https://github.com/ofskean/frossl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.02903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02903"}},"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/ofskean/frossl","reach":{"status":"ok"}}],"summary":{"ran":5,"unverified":7},"by_repo_kind":{"official":{"samples":12,"ran":5,"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":12,"samples":[{"code_sha256_prefix":"132a949a804eb81e","entry":"barlow_loss_func","repo":"ofskean/frossl","repo_kind":"official","path":"solo/losses/barlow.py","file_url":"https://github.com/ofskean/frossl/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"132a949a804eb81e"}},{"code_sha256_prefix":"273532e06cb3967e","entry":"byol_loss_func","repo":"ofskean/frossl","repo_kind":"official","path":"solo/losses/byol.py","file_url":"https://github.com/ofskean/frossl/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"273532e06cb3967e"}},{"code_sha256_prefix":"5d1862937c9d7a74","entry":"cosine_similarity_loss_func","repo":"ofskean/frossl","repo_kind":"official","path":"solo/losses/empssl.py","file_url":"https://github.com/ofskean/frossl/blob/HEAD/solo/losses/empssl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5d1862937c9d7a74"}},{"code_sha256_prefix":"a07d9a7525702b80","entry":"mae_loss_func","repo":"ofskean/frossl","repo_kind":"official","path":"solo/losses/mae.py","file_url":"https://github.com/ofskean/frossl/blob/HEAD/solo/losses/mae.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a07d9a7525702b80"}},{"code_sha256_prefix":"3e6a557bf1ad83d9","entry":"patchify","repo":"ofskean/frossl","repo_kind":"official","path":"solo/losses/mae.py","file_url":"https://github.com/ofskean/frossl/blob/HEAD/solo/losses/mae.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3e6a557bf1ad83d9"}},{"code_sha256_prefix":"c476395240281b5c","entry":"calculate_TCR","repo":"ofskean/frossl","repo_kind":"official","path":"solo/losses/empssl.py","file_url":"https://github.com/ofskean/frossl/blob/HEAD/solo/losses/empssl.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":"c476395240281b5c"}},{"code_sha256_prefix":"c243f30656ecb72f","entry":"calculate_TCR_for_list","repo":"ofskean/frossl","repo_kind":"official","path":"solo/losses/empssl.py","file_url":"https://github.com/ofskean/frossl/blob/HEAD/solo/losses/empssl.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":"c243f30656ecb72f"}},{"code_sha256_prefix":"ce432f2e9653c7a3","entry":"deepclusterv2_loss_func","repo":"ofskean/frossl","repo_kind":"official","path":"solo/losses/deepclusterv2.py","file_url":"https://github.com/ofskean/frossl/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ce432f2e9653c7a3"}},{"code_sha256_prefix":"398c3b54687b75b2","entry":"get_vne","repo":"ofskean/frossl","repo_kind":"official","path":"solo/losses/ivne.py","file_url":"https://github.com/ofskean/frossl/blob/HEAD/solo/losses/ivne.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":"398c3b54687b75b2"}},{"code_sha256_prefix":"46defae585608157","entry":"invariance_loss","repo":"ofskean/frossl","repo_kind":"official","path":"solo/losses/corinfomax.py","file_url":"https://github.com/ofskean/frossl/blob/HEAD/solo/losses/corinfomax.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":"46defae585608157"}},{"code_sha256_prefix":"4995c4ff2d48e212","entry":"ivne_loss_func","repo":"ofskean/frossl","repo_kind":"official","path":"solo/losses/ivne.py","file_url":"https://github.com/ofskean/frossl/blob/HEAD/solo/losses/ivne.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":"4995c4ff2d48e212"}},{"code_sha256_prefix":"de64f0dbc597b757","entry":"multiview_frossl_loss_func","repo":"ofskean/frossl","repo_kind":"official","path":"solo/losses/frossl.py","file_url":"https://github.com/ofskean/frossl/blob/HEAD/solo/losses/frossl.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":"de64f0dbc597b757"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}