English

Bootstrap Masked Visual Modeling via Hard Patches Mining

Computer Vision and Pattern Recognition 2023-12-22 v1

Abstract

Masked visual modeling has attracted much attention due to its promising potential in learning generalizable representations. Typical approaches urge models to predict specific contents of masked tokens, which can be intuitively considered as teaching a student (the model) to solve given problems (predicting masked contents). Under such settings, the performance is highly correlated with mask strategies (the difficulty of provided problems). We argue that it is equally important for the model to stand in the shoes of a teacher to produce challenging problems by itself. Intuitively, patches with high values of reconstruction loss can be regarded as hard samples, and masking those hard patches naturally becomes a demanding reconstruction task. To empower the model as a teacher, we propose Hard Patches Mining (HPM), predicting patch-wise losses and subsequently determining where to mask. Technically, we introduce an auxiliary loss predictor, which is trained with a relative objective to prevent overfitting to exact loss values. Also, to gradually guide the training procedure, we propose an easy-to-hard mask strategy. Empirically, HPM brings significant improvements under both image and video benchmarks. Interestingly, solely incorporating the extra loss prediction objective leads to better representations, verifying the efficacy of determining where is hard to reconstruct. The code is available at https://github.com/Haochen-Wang409/HPM.

Keywords

Cite

@article{arxiv.2312.13714,
  title  = {Bootstrap Masked Visual Modeling via Hard Patches Mining},
  author = {Haochen Wang and Junsong Fan and Yuxi Wang and Kaiyou Song and Tiancai Wang and Xiangyu Zhang and Zhaoxiang Zhang},
  journal= {arXiv preprint arXiv:2312.13714},
  year   = {2023}
}

Comments

arXiv admin note: substantial text overlap with arXiv:2304.05919

R2 v1 2026-06-28T13:58:31.136Z