{"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/context-autoencoder-for-self-supervised","title":"Context Autoencoder for Self-Supervised Representation Learning","arxiv_id":"2202.03026","date":"2022-02-07","proceeding":null,"authors":["Xiaokang Chen","Mingyu Ding","Xiaodi Wang","Ying Xin","Shentong Mo","Yunhao Wang","Shumin Han","Ping Luo","Gang Zeng","Jingdong Wang"],"abstract":"We present a novel masked image modeling (MIM) approach, context autoencoder (CAE), for self-supervised representation pretraining. We pretrain an encoder by making predictions in the encoded representation space. The pretraining tasks include two tasks: masked representation prediction - predict the representations for the masked patches, and masked patch reconstruction - reconstruct the masked patches. The network is an encoder-regressor-decoder architecture: the encoder takes the visible patches as input; the regressor predicts the representations of the masked patches, which are expected to be aligned with the representations computed from the encoder, using the representations of visible patches and the positions of visible and masked patches; the decoder reconstructs the masked patches from the predicted encoded representations. The CAE design encourages the separation of learning the encoder (representation) from completing the pertaining tasks: masked representation prediction and masked patch reconstruction tasks, and making predictions in the encoded representation space empirically shows the benefit to representation learning. We demonstrate the effectiveness of our CAE through superior transfer performance in downstream tasks: semantic segmentation, object detection and instance segmentation, and classification. The code will be available at https://github.com/Atten4Vis/CAE.","url_abs":"https://arxiv.org/abs/2202.03026v3","url_pdf":"https://arxiv.org/pdf/2202.03026v3.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":"context-autoencoder-for-self-supervised","repo_url":"https://github.com/atten4vis/cae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"context-autoencoder-for-self-supervised","repo_url":"https://github.com/lxtGH/CAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"context-autoencoder-for-self-supervised","repo_url":"https://github.com/open-mmlab/mmselfsup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"context-autoencoder-for-self-supervised","repo_url":"https://github.com/PaddlePaddle/PLSC/tree/master/task/ssl/cae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"context-autoencoder-for-self-supervised","repo_url":"https://github.com/PaddlePaddle/PaddleFL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"context-autoencoder-for-self-supervised","repo_url":"https://github.com/PaddlePaddle/VIMER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"CAE (ViT-L, Mask R-CNN, 1x schedule)","rank_in_archive_order":56,"of":220,"metrics":{"box AP":"54.5"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on-1","task":"Self-Supervised Image Classification","dataset":"ImageNet (finetuned)","model":"CAE (ViT-L/16)","rank_in_archive_order":15,"of":65,"metrics":{"Number of Params":"307M","Top 1 Accuracy":"86.3%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"CAE (ViT-L, UperNet)","rank_in_archive_order":57,"of":235,"metrics":{"Validation mIoU":"54.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2202.03026","atlas_url":"https://app.syntology.ai/?focus=2202.03026","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":"2202.03026"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2202.03026\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2202.03026"},"call":"get_concepts_for_paper(arxiv_id=\"2202.03026\")"}],"by_repo":[{"repo":"atten4vis/cae","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lxtGH/CAE","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"open-mmlab/mmselfsup","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2303.02416"],"harvested_for_calls":[{"arxiv_id":"2303.02416","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2303.02416"},"call":"get_harvested_code_for_paper(arxiv_id=\"2303.02416\")"}]},{"repo":"PaddlePaddle/PLSC","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2210.09461"],"harvested_for_calls":[{"arxiv_id":"2210.09461","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.09461"},"call":"get_harvested_code_for_paper(arxiv_id=\"2210.09461\")"}]},{"repo":"PaddlePaddle/PaddleFL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"PaddlePaddle/VIMER","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"7dfc835086c04f90618fbb21763a7589343b977b23c00e45b02a1f73c10f6060","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}