Abstract
In this paper, we introduce Saliency-Based Adaptive Masking (SBAM), a novel and cost-effective approach that significantly enhances the pre-training performance of Masked Image Modeling (MIM) approaches by prioritizing token salience. Our method provides robustness against variations in masking ratios, effectively mitigating the performance instability issues common in existing methods. This relaxes the sensitivity of MIM-based pre-training to masking ratios, which in turn allows us to propose an adaptive strategy for `tailored' masking ratios for each data sample, which no existing method can provide. Toward this goal, we propose an Adaptive Masking Ratio (AMR) strategy that dynamically adjusts the proportion of masking for the unique content of each image based on token salience. We show that our method significantly improves over the state-of-the-art in mask-based pre-training on the ImageNet-1K dataset.
Abstract (translated)
在本文中，我们提出了Saliency-Based Adaptive Masking（SBAM）方法，一种新颖且成本效益高的方法，它通过优先考虑token的 salience显著增强了基于掩码图像建模（MIM）方法的预训练性能。我们的方法对于掩码比的变化具有鲁棒性，有效缓解了现有方法中常见的性能不稳定问题。这使得基于MIM的预训练对掩码比的变化更加敏感，进而允许我们为每个数据样本提出自适应的掩码比策略，而现有的方法无法实现。为此，我们提出了一个自适应掩码比（AMR）策略，根据token的 salience动态调整每个图像的掩码比例。我们证明了我们的方法在ImageNet-1K数据集上的基于掩码的预训练方面显著优于现有方法。
URL
https://arxiv.org/abs/2404.08327
