Information-Theoretic Visual Explanation for Black-Box Classifiers
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.
Code (1)
Similar Papers 제목 키워드 기반
Multiple Different Black Box Explanations for Image Classifiers
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
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
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 AttributionCausal Explanations for Image Classifiers
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
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…