用奇异值分解让ViT更关注前景，提升分类准确率
SVD-ViT: Does SVD Make Vision Transformers Attend More to the Foreground?
- 通过SVD提取前景特征的奇异向量，强化关键信息学习
- 在ImageNet上提升分类准确率，同时减少背景噪声影响
- 适合需要精准前景感知的视觉任务，如医学图像分析
视觉变压器（ViT）作为大规模基础模型已得到广泛认可。然而，由于自注意力机制全局操作，缺乏明确区分前景与背景的机制，导致模型可能学习到无关的背景特征和伪影，从而降低分类性能。为解决此问题，我们提出SVD-ViT，利用奇异值分解（SVD）优先学习前景特征。SVD-ViT包含三个组件——SPC模块、SSVA和ID-RSVD——通过提取并聚合捕捉物体前景信息的奇异向量，抑制任务无关因素如背景噪声和伪影。实验结果表明，该方法提升了分类准确率，有效学习了富有信息量的前景表示，同时降低了背景噪声的影响。
原文摘要 · Abstract (English)
Vision Transformers (ViT) have been established as large-scale foundation models. However, because self-attention operates globally, they lack an explicit mechanism to distinguish foreground from background. As a result, ViT may learn unnecessary background features and artifacts, leading to degraded classification performance. To address this issue, we propose SVD-ViT, which leverages singular value decomposition (SVD) to prioritize the learning of foreground features. SVD-ViT consists of three components-\textbf{SPC module}, \textbf{SSVA}, and \textbf{ID-RSVD}-and suppresses task-irrelevant factors such as background noise and artifacts by extracting and aggregating singular vectors that capture object foreground information. Experimental results demonstrate that our method improves classification accuracy and effectively learns informative foreground representations while reducing the impact of background noise.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。