Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction
share
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 classification, outperforming MAE by 0.5 LoMaR on 384×384 images, it can reach 85.4 MAE by 0.6 object detection and 0.5 AP^mask 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 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 will be publicly available.
READ FULL TEXT
