activity
20242026
most citedStatistical Test for Attention Map in Vision Transformer

1 citations · 1 across the 10 of their papers we have counts for

collaborators

10 papers

stat.ML2026

Automatic Statistical Test for Rationally Expressible Algorithms by Selective Inference, with Applications to Feature Selection

Teruyuki Katsuoka, Tomohiro Shiraishi, Shuichi Nishino +1

Selective inference (SI) provides statistically valid -values for hypotheses selected by applying an algorithm to the data, correcting for the bias that arises when the same dat…

stat.ML2026

Post-ADC Inference: Valid Inference After Active Data Collection

Shuichi Nishino, Tomohiro Shiraishi, Teruyuki Katsuoka +1

The validity of statistical inference depends critically on how data are collected. When data gathered through active data collection (ADC) are reused for a post-hoc inferential ta…

stat.ML2025

Statistical Test for Saliency Maps of Graph Neural Networks via Selective Inference

Shuichi Nishino, Tomohiro Shiraishi, Teruyuki Katsuoka +1

Graph Neural Networks (GNNs) have gained prominence for their ability to process graph-structured data across various domains. However, interpreting GNN decisions remains a signifi…

stat.ML2025

Quantifying Statistical Significance of Deep Nearest Neighbor Anomaly Detection via Selective Inference

Mizuki Niihori, Shuichi Nishino, Teruyuki Katsuoka +3

In real-world applications, anomaly detection (AD) often operates without access to anomalous data, necessitating semi-supervised methods that rely solely on normal data. Among the…

stat.ML2025

Change Point Detection in the Frequency Domain with Statistical Reliability

Akifumi Yamada, Tomohiro Shiraishi, Shuichi Nishino +3

Effective condition monitoring in complex systems requires identifying change points (CPs) in the frequency domain, as the structural changes often arise across multiple frequencie…

cs.LG2025

si4onnx: A Python package for Selective Inference in Deep Learning Models

Teruyuki Katsuoka, Tomohiro Shiraishi, Daiki Miwa +2

In this paper, we introduce si4onnx, a package for performing selective inference on deep learning models. Techniques such as CAM in XAI and reconstruction-based anomaly detection…