{"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/modality-agnostic-self-supervised-learning","title":"Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder","arxiv_id":"2310.16318","date":"2023-10-25","proceeding":"NeurIPS 2023 11","authors":[],"abstract":"Despite its practical importance across a wide range of modalities, recent advances in self-supervised learning (SSL) have been primarily focused on a few well-curated domains, e.g., vision and language, often relying on their domain-specific knowledge. For example, Masked Auto-Encoder (MAE) has become one of the popular architectures in these domains, but less has explored its potential in other modalities. In this paper, we develop MAE as a unified, modality-agnostic SSL framework. In turn, we argue meta-learning as a key to interpreting MAE as a modality-agnostic learner, and propose enhancements to MAE from the motivation to jointly improve its SSL across diverse modalities, coined MetaMAE as a result. Our key idea is to view the mask reconstruction of MAE as a meta-learning task: masked tokens are predicted by adapting the Transformer meta-learner through the amortization of unmasked tokens. Based on this novel interpretation, we propose to integrate two advanced meta-learning techniques. First, we adapt the amortized latent of the Transformer encoder using gradient-based meta-learning to enhance the reconstruction. Then, we maximize the alignment between amortized and adapted latents through task contrastive learning which guides the Transformer encoder to better encode the task-specific knowledge. Our experiment demonstrates the superiority of MetaMAE in the modality-agnostic SSL benchmark (called DABS), significantly outperforming prior baselines. Code is available at https://github.com/alinlab/MetaMAE.","url_abs":"https://arxiv.org/abs/2310.16318v1","url_pdf":"https://arxiv.org/pdf/2310.16318v1.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":"modality-agnostic-self-supervised-learning","repo_url":"https://github.com/alinlab/metamae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"mae","method_name":"MAE"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.16318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16318"}},"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":"deterministic:regex_extraction","url":"https://github.com/alinlab/MetaMAE","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alinlab/metamae","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":5},"by_repo_kind":{"listed":{"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":8,"samples":[{"code_sha256_prefix":"47b0337d90da423b","entry":"UnifiedPatchEmbed","repo":"alinlab/metamae","repo_kind":"listed","path":"models.py","file_url":"https://github.com/alinlab/metamae/blob/HEAD/models.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":"47b0337d90da423b"}},{"code_sha256_prefix":"b9a33eb920b9d3f1","entry":"accuracy","repo":"alinlab/MetaMAE","repo_kind":"listed","path":"linear_evaluation.py","file_url":"https://github.com/alinlab/MetaMAE/blob/HEAD/linear_evaluation.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":"b9a33eb920b9d3f1"}},{"code_sha256_prefix":"d98aa6b239eec82a","entry":"binary_accuracy","repo":"alinlab/MetaMAE","repo_kind":"listed","path":"linear_evaluation.py","file_url":"https://github.com/alinlab/MetaMAE/blob/HEAD/linear_evaluation.py","link_basis":"first_harvest_node","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":"d98aa6b239eec82a"}},{"code_sha256_prefix":"3f952d0ff510309b","entry":"MAE","repo":"alinlab/metamae","repo_kind":"listed","path":"models.py","file_url":"https://github.com/alinlab/metamae/blob/HEAD/models.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":"3f952d0ff510309b"}},{"code_sha256_prefix":"85bcdb61bb35505b","entry":"MetaMAE","repo":"alinlab/metamae","repo_kind":"listed","path":"models.py","file_url":"https://github.com/alinlab/metamae/blob/HEAD/models.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":"85bcdb61bb35505b"}},{"code_sha256_prefix":"33c3be189afc6b97","entry":"get_1d_sincos_pos_embed","repo":"alinlab/metamae","repo_kind":"listed","path":"models.py","file_url":"https://github.com/alinlab/metamae/blob/HEAD/models.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":"33c3be189afc6b97"}},{"code_sha256_prefix":"d599b95b94498131","entry":"get_2d_sincos_pos_embed","repo":"alinlab/MetaMAE","repo_kind":"listed","path":"models.py","file_url":"https://github.com/alinlab/MetaMAE/blob/HEAD/models.py","link_basis":"plan_row","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":"d599b95b94498131"}},{"code_sha256_prefix":"1b09d250011e5780","entry":"get_model","repo":"alinlab/MetaMAE","repo_kind":"listed","path":"models.py","file_url":"https://github.com/alinlab/MetaMAE/blob/HEAD/models.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":"1b09d250011e5780"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}