paper-with-me

홈 › Papers

Information-Theoretic Visual Explanation for Black-Box Classifiers

2020-09-23 · Jihun Yi, Eunji Kim, Siwon Kim, Sungroh Yoon

In this work, we attempt to explain the prediction of any black-box classifier from an information-theoretic perspective. For each input feature, we compare the classifier outputs with and without that feature using two information-theoretic metrics. Accordingly, we obtain two attribution maps--an information gain (IG) map and a point-wise mutual information (PMI) map. IG map provides a class-independent answer to "How informative is each pixel?", and PMI map offers a class-specific explanation of "How much does each pixel support a specific class?" Compared to existing methods, our method improves the correctness of the attribution maps in terms of a quantitative metric. We also provide a detailed analysis of an ImageNet classifier using the proposed method, and the code is available online.

📄 PDF Abstract BibTeX arXiv:2009.11150

Code (1)

nuclearboy95/XAI-Information-Theoretic-Explanation 공식 구현 tf

Similar Papers 제목 키워드 기반

Multiple Different Black Box Explanations for Image Classifiers

2023-09-25 · Hana Chockler, David A. Kelly, Daniel Kroening

Existing explanation tools for image classifiers usually give only a single explanation for an image's classification. For many images, however, both humans and image classifiers accept more than one explanation for the …

Generative causal explanations of black-box classifiers

2020-06-24 · NeurIPS 2020 12 · Matthew O'Shaughnessy, Gregory Canal, Marissa Connor, Mark Davenport 외

We develop a method for generating causal post-hoc explanations of black-box classifiers based on a learned low-dimensional representation of the data. The explanation is causal in the sense that changing learned latent …

OCCAM: Open-set Causal Concept explAnation and Ontology induction for black-box vision Models

2026-05-18 · Chiara Maria Russo, Simone Carnemolla, Simone Palazzo, Daniela Giordano 외 arxiv

Interpreting the decisions of deep image classifiers remains challenging, particularly in black-box settings where model internals are inaccessible. We introduce OCCAM, a framework for open-set causal concept explanation…

Image Attribution

Causal Explanations for Image Classifiers

2024-11-13 · Hana Chockler, David A. Kelly, Daniel Kroening, Youcheng Sun

Existing algorithms for explaining the output of image classifiers use different definitions of explanations and a variety of techniques to extract them. However, none of the existing tools use a principled approach base…

Boundary-Aware Uncertainty for Feature Attribution Explainers

2022-10-05 · Davin Hill, Aria Masoomi, Max Torop, Sandesh Ghimire 외

Post-hoc explanation methods have become a critical tool for understanding black-box classifiers in high-stakes applications. However, high-performing classifiers are often highly nonlinear and can exhibit complex behavi…