2024/01/16 by Tomohiro Shiraishi, Daiki Miwa, Shiraishi, Tomohiro +8 · 2 citations
Computer Science · Engineering · #FOS: Computer and information sciences #Image and Signal Denoising Methods #Industrial Vision Systems and Defect Detection #Infrared Target Detection Methodologies #Machine Learning (cs.LG) #Machine Learning (stat.ML)
paper · pdf · doi:10.48550/arxiv.2401.08169
openalex publication_date 2024/01/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
The Vision Transformer (ViT) demonstrates exceptional performance in various computer vision tasks. Attention is crucial for ViT to capture complex wide-ranging relationships among image patches, allowing the model to weigh the importance of image patches and aiding our understanding of the decision-making process. However, when utilizing the attention of ViT as evidence in high-stakes decision-making tasks such as medical diagnostics, a challenge arises due to the potential of attention mechanisms erroneously focusing on irrelevant regions. In this study, we propose a statistical test for ViT's attentions, enabling us to use the attentions as reliable quantitative evidence indicators for ViT's decision-making with a rigorously controlled error rate. Using the framework called selective inference, we quantify the statistical significance of attentions in the form of p-values, which enables the theoretically grounded quantification of the false positive detection probability of attentions. We demonstrate the validity and the effectiveness of the proposed method through numerical experiments and applications to brain image diagnoses.