{"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/mixmim-mixed-and-masked-image-modeling-for","title":"MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers","arxiv_id":"2205.13137","date":"2022-05-26","proceeding":"CVPR 2023 1","authors":["Jihao Liu","Xin Huang","Jinliang Zheng","Yu Liu","Hongsheng Li"],"abstract":"In this paper, we propose Mixed and Masked AutoEncoder (MixMAE), a simple but efficient pretraining method that is applicable to various hierarchical Vision Transformers. Existing masked image modeling (MIM) methods for hierarchical Vision Transformers replace a random subset of input tokens with a special [MASK] symbol and aim at reconstructing original image tokens from the corrupted image. However, we find that using the [MASK] symbol greatly slows down the training and causes pretraining-finetuning inconsistency, due to the large masking ratio (e.g., 60% in SimMIM). On the other hand, MAE does not introduce [MASK] tokens at its encoder at all but is not applicable for hierarchical Vision Transformers. To solve the issue and accelerate the pretraining of hierarchical models, we replace the masked tokens of one image with visible tokens of another image, i.e., creating a mixed image. We then conduct dual reconstruction to reconstruct the two original images from the mixed input, which significantly improves efficiency. While MixMAE can be applied to various hierarchical Transformers, this paper explores using Swin Transformer with a large window size and scales up to huge model size (to reach 600M parameters). Empirical results demonstrate that MixMAE can learn high-quality visual representations efficiently. Notably, MixMAE with Swin-B/W14 achieves 85.1% top-1 accuracy on ImageNet-1K by pretraining for 600 epochs. Besides, its transfer performances on the other 6 datasets show that MixMAE has better FLOPs / performance tradeoff than previous popular MIM methods. Code is available at https://github.com/Sense-X/MixMIM.","url_abs":"https://arxiv.org/abs/2205.13137v4","url_pdf":"https://arxiv.org/pdf/2205.13137v4.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":"mixmim-mixed-and-masked-image-modeling-for","repo_url":"https://github.com/sense-x/mixmim","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"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":"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":"mim","method_name":"MIM"},{"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":"stochastic-depth","method_name":"Stochastic Depth"},{"method_slug":"swin-transformer","method_name":"Swin Transformer"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MixMIM-B","rank_in_archive_order":259,"of":1060,"metrics":{"GFLOPs":"16.3","Number of params":"88M","Top 1 Accuracy":"85.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-places205","task":"Image Classification","dataset":"Places205","model":"MixMIM-L","rank_in_archive_order":2,"of":15,"metrics":{"Top 1 Accuracy":"69.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-places205","task":"Image Classification","dataset":"Places205","model":"MixMIM-B","rank_in_archive_order":4,"of":15,"metrics":{"Top 1 Accuracy":"68.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-places365","task":"Image Classification","dataset":"Places365","model":"MixMIM-L(ViT-L)","rank_in_archive_order":4,"of":7,"metrics":{"Top 1 Accuracy":"60.3"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-places365","task":"Image Classification","dataset":"Places365","model":"MixMIM-B (ViT)","rank_in_archive_order":7,"of":7,"metrics":{"Top 1 Accuracy":"58.9"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"MixMIM-L","rank_in_archive_order":17,"of":60,"metrics":{"Top-1 Accuracy":"80.3%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"MixMIM-B","rank_in_archive_order":23,"of":60,"metrics":{"Top-1 Accuracy":"77.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-inaturalist-2019","task":"Image Classification","dataset":"iNaturalist 2019","model":"MixMIM-L","rank_in_archive_order":4,"of":22,"metrics":{"Top-1 Accuracy":"83.9"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-2017","task":"Object Detection","dataset":"COCO 2017","model":"MixMIM-L","rank_in_archive_order":12,"of":24,"metrics":{"mAP":"54.1"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-2017","task":"Object Detection","dataset":"COCO 2017","model":"MixMIM-B","rank_in_archive_order":14,"of":24,"metrics":{"mAP":"52.2"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"MixMIM-L","rank_in_archive_order":37,"of":95,"metrics":{"mIoU":"53.8"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"MixMIM-B","rank_in_archive_order":51,"of":95,"metrics":{"mIoU":"50.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.13137","atlas_url":"https://app.syntology.ai/?focus=2205.13137","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":"2205.13137"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2205.13137\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2205.13137"},"call":"get_concepts_for_paper(arxiv_id=\"2205.13137\")"}],"by_repo":[{"repo":"sense-x/mixmim","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"43250912285096817ab6275b6807cac75052f885e09821870589caf11040ca02","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}