Presentation | 2023-06-29 Selective Inference for DNN-driven Saliency Map Daiki Miwa, Vo Nguyen Le Duy, Tomohiro Shiraishi, Ichiro Takeuchi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The usefulness of image classification using DNN models has been confirmed in various fields, but the prediction mechanism of these models cannot be fully understood. Therefore, a type of methods called Saliency Map has been proposed to visualize the explanation of predictions, but issues regarding the reliability of the results have been pointed out. In this study, we consider evaluating the reliability of Saliency Map using the framework of statistical hypothesis testing. Unfortunately, conventional statistical hypothesis testing cannot perform valid tests due to the selection bias caused by DNNs. Therefore, we introduce the concept of selective inference, which has been actively studied in recent years, and propose a valid testing method that can properly control Type I Error Rate. In this paper, we specifically report the results when the proposed method is applied to saliency maps obtained by Grad-cam, one of the most frequently used Saliency Map techniques. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Selective Inference / Statistical Hypothesis Testing / Saliency Map / Deep Learning |
Paper # | NC2023-5,IBISML2023-5 |
Date of Issue | 2023-06-22 (NC, IBISML) |
Conference Information | |
Committee | NC / IBISML / IPSJ-BIO / IPSJ-MPS |
---|---|
Conference Date | 2023/6/29(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | OIST Conference Center |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Hirokazu Tanaka(Tokyo City Univ.) / Masashi Sugiyama(Univ. of Tokyo) |
Vice Chair | Jun Izawa(Univ. of Tsukub) / Toshihiro Kamishima(AIST) / Koji Tsuda(Univ. of Tokyo) |
Secretary | Jun Izawa(NTT) / Toshihiro Kamishima(NAIST) / Koji Tsuda(NTT) / (Hokkaido Univ.) |
Assistant | Yoshimasa Tawatsuji(Waseda Univ.) / Takato Horii(Osaka Univ.) / Yoshinobu Kawahara(Osaka Univ.) / Taiji Suzuki(Tokyo Inst. of Tech.) |
Paper Information | |
Registration To | Technical Committee on Neurocomputing / Technical Committee on Information-Based Induction Sciences and Machine Learning / Special Interest Group on Bioinformatics and Genomics / Special Interest Group on Mathematical Modeling and Problem Solving |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Selective Inference for DNN-driven Saliency Map |
Sub Title (in English) | |
Keyword(1) | Selective Inference |
Keyword(2) | Statistical Hypothesis Testing |
Keyword(3) | Saliency Map |
Keyword(4) | Deep Learning |
1st Author's Name | Daiki Miwa |
1st Author's Affiliation | Nagoya Institute of Technology(NITech) |
2nd Author's Name | Vo Nguyen Le Duy |
2nd Author's Affiliation | RIKEN(RIKEN) |
3rd Author's Name | Tomohiro Shiraishi |
3rd Author's Affiliation | Nagoya University(Nagoya Univ.) |
4th Author's Name | Ichiro Takeuchi |
4th Author's Affiliation | Nagoya University/RIKEN(Nagoya Univ./RIKEN) |
Date | 2023-06-29 |
Paper # | NC2023-5,IBISML2023-5 |
Volume (vol) | vol.123 |
Number (no) | NC-90,IBISML-91 |
Page | pp.pp.30-34(NC), pp.30-34(IBISML), |
#Pages | 5 |
Date of Issue | 2023-06-22 (NC, IBISML) |