{"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/masked-autoencoders-are-efficient-class","title":"Masked Autoencoders are Efficient Class Incremental Learners","arxiv_id":"2308.12510","date":"2023-08-24","proceeding":"ICCV 2023 1","authors":["Jiang-Tian Zhai","Xialei Liu","Andrew D. Bagdanov","Ke Li","Ming-Ming Cheng"],"abstract":"Class Incremental Learning (CIL) aims to sequentially learn new classes while avoiding catastrophic forgetting of previous knowledge. We propose to use Masked Autoencoders (MAEs) as efficient learners for CIL. MAEs were originally designed to learn useful representations through reconstructive unsupervised learning, and they can be easily integrated with a supervised loss for classification. Moreover, MAEs can reliably reconstruct original input images from randomly selected patches, which we use to store exemplars from past tasks more efficiently for CIL. We also propose a bilateral MAE framework to learn from image-level and embedding-level fusion, which produces better-quality reconstructed images and more stable representations. Our experiments confirm that our approach performs better than the state-of-the-art on CIFAR-100, ImageNet-Subset, and ImageNet-Full. The code is available at https://github.com/scok30/MAE-CIL .","url_abs":"https://arxiv.org/abs/2308.12510v1","url_pdf":"https://arxiv.org/pdf/2308.12510v1.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":"masked-autoencoders-are-efficient-class","repo_url":"https://github.com/scok30/mae-cil","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"}],"methods":[{"method_slug":"mae","method_name":"MAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.12510","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12510"}},"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/scok30/MAE-CIL","reach":null}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"464cf541506bd484","entry":"PatchEmbed","repo":"scok30/MAE-CIL","repo_kind":"official","path":"continual/vit.py","file_url":"https://github.com/scok30/MAE-CIL/blob/HEAD/continual/vit.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":"464cf541506bd484"}},{"code_sha256_prefix":"e1d62aeb525afd2a","entry":"VisionTransformer","repo":"scok30/MAE-CIL","repo_kind":"official","path":"continual/vit.py","file_url":"https://github.com/scok30/MAE-CIL/blob/HEAD/continual/vit.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":"e1d62aeb525afd2a"}},{"code_sha256_prefix":"36555c3eaf0df8b4","entry":"_init_vit_weights","repo":"scok30/MAE-CIL","repo_kind":"official","path":"continual/vit.py","file_url":"https://github.com/scok30/MAE-CIL/blob/HEAD/continual/vit.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":"36555c3eaf0df8b4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}