SI-CLAD computes selective-inference p-values for DBSCAN-detected anomalies, controlling the false positive rate at a user-specified level while raising true detection rates.
Statistical Test for Attention Map in Vision Transformer
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
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.
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Statistical Inference for Clustering-based Anomaly Detection
SI-CLAD computes selective-inference p-values for DBSCAN-detected anomalies, controlling the false positive rate at a user-specified level while raising true detection rates.