Papers › Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction

Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction

1 Jun 2022arXiv:2206.00790archive 2025-07-28

Jun Chen, Ming Hu, Boyang Li, Mohamed Elhoseiny

Self-supervised learning for computer vision has achieved tremendous progress and improved many downstream vision tasks such as image classification, semantic segmentation, and object detection. Among these, generative self-supervised vision learning approaches such as MAE and BEiT show promising performance. However, their global masked reconstruction mechanism is computationally demanding. To address this issue, we propose local masked reconstruction (LoMaR), a simple yet effective approach that performs masked reconstruction within a small window of 7×7 patches on a simple Transformer encoder, improving the trade-off between efficiency and accuracy compared to global masked reconstruction over the entire image. Extensive experiments show that LoMaR reaches 84.1% top-1 accuracy on ImageNet-1K classification, outperforming MAE by 0.5%. After finetuning the pretrained LoMaR on 384×384 images, it can reach 85.4% top-1 accuracy, surpassing MAE by 0.6%. On MS COCO, LoMaR outperforms MAE by 0.5 APᵇᵒˣ on object detection and 0.5 APᵐᵃˢᵏ on instance segmentation. LoMaR is especially more computation-efficient on pretraining high-resolution images, e.g., it is 3.1× faster than MAE with 0.2% higher classification accuracy on pretraining 448×448 images. This local masked reconstruction learning mechanism can be easily integrated into any other generative self-supervised learning approach. Our code is publicly available in https://github.com/junchen14/LoMaR.

Paper PDF Code

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

Code

junchen14/LoMaR officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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 Classification Instance Segmentation Object Detection Self-Supervised Learning Semantic Segmentation image-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer MAE Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

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