对称掩码策略提升掩码图像建模的性能
Symmetric masking strategy enhances the performance of Masked Image Modeling
AI总结：
针对现有掩码图像建模依赖随机掩码策略、资源消耗高且普适性差的问题，提出基于对称掩码的SymMIM训练流水线，有效捕捉全局局部特征，在ImageNet及多下游任务上取得SOTA性能。
摘要：
掩码图像建模（Masked Image Modeling，MIM）是自监督学习中的一项技术，其核心是通过估计随机掩码区域中缺失的像素，从未标注图像中获取细粒度视觉表征。该技术已被证实是Vision Transformers（ViTs）预训练的有力工具，在各类任务中均取得了出色的结果。然而，大多数MIM方法高度依赖随机掩码策略来构建前置任务，该策略需要大量试验才能确定最优丢弃比例，资源消耗极大，要求模型预训练800到1600个epoch不等，且这种方法可能并不适用于所有数据集。在本研究中，我们提出了一种新型掩码策略，可有效帮助模型捕捉全局和局部特征。基于该掩码策略，我们推出了所提出的MIM训练流水线SymMIM。SymMIM使用ViT-Large在ImageNet上取得了85.9%的全新SOTA准确率，并且在图像分类、语义分割、目标检测、实例分割等下游任务上均超越了此前的SOTA水平。
英文摘要：
Masked Image Modeling (MIM) is a technique in self-supervised learning that focuses on acquiring detailed visual representations from unlabeled images by estimating the missing pixels in randomly masked sections. It has proven to be a powerful tool for the preliminary training of Vision Transformers (ViTs), yielding impressive results across various tasks. Nevertheless, most MIM methods heavily depend on the random masking strategy to formulate the pretext task. This strategy necessitates numerous trials to ascertain the optimal dropping ratio, which can be resource-intensive, requiring the model to be pre-trained for anywhere between 800 to 1600 epochs. Furthermore, this approach may not be suitable for all datasets. In this work, we propose a new masking strategy that effectively helps the model capture global and local features. Based on this masking strategy, SymMIM, our proposed training pipeline for MIM is introduced. SymMIM achieves a new SOTA accuracy of 85.9\% on ImageNet using ViT-Large and surpasses previous SOTA across downstream tasks such as image classification, semantic segmentation, object detection, instance segmentation tasks, and so on.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
