Papers › MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision...

MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers

26 May 2022CVPR 2023 1arXiv:2205.13137archive 2025-07-28

Jihao Liu, Xin Huang, Jinliang Zheng, Yu Liu, Hongsheng Li

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.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

sense-x/mixmim officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationObject DetectionRepresentation LearningSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet MixMIM-B GFLOPs 16.3 #259 of 1060 Archive leaderboard report
Image Classification ImageNet MixMIM-B Number of params 88M #259 of 1060 Archive leaderboard report
Image Classification ImageNet MixMIM-B Top 1 Accuracy 85.1% #259 of 1060 Archive leaderboard report
Image Classification Places205 MixMIM-L Top 1 Accuracy 69.3 #2 of 15 Archive leaderboard report
Image Classification Places205 MixMIM-B Top 1 Accuracy 68.3 #4 of 15 Archive leaderboard report
Image Classification Places365 MixMIM-L(ViT-L) Top 1 Accuracy 60.3 #4 of 7 Archive leaderboard report
Image Classification Places365 MixMIM-B (ViT) Top 1 Accuracy 58.9 #7 of 7 Archive leaderboard report
Image Classification iNaturalist 2018 MixMIM-L Top-1 Accuracy 80.3% #17 of 60 Archive leaderboard report
Image Classification iNaturalist 2018 MixMIM-B Top-1 Accuracy 77.5% #23 of 60 Archive leaderboard report
Image Classification iNaturalist 2019 MixMIM-L Top-1 Accuracy 83.9 #4 of 22 Archive leaderboard report
Object Detection COCO 2017 MixMIM-L mAP 54.1 #12 of 24 Archive leaderboard report
Object Detection COCO 2017 MixMIM-B mAP 52.2 #14 of 24 Archive leaderboard report
Semantic Segmentation ADE20K val MixMIM-L mIoU 53.8 #37 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val MixMIM-B mIoU 50.3 #51 of 95 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMAEMIMMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxStochastic DepthSwin TransformerTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections