PACE: Posthoc Architecture-Agnostic Concept Extractor for Explaining CNNs release_owt3ys2gtzhphbvndtdxqy5nku

by Vidhya Kamakshi, Uday Gupta, Narayanan C Krishnan

Released as a article .

2021  

Abstract

Deep CNNs, though have achieved the state of the art performance in image classification tasks, remain a black-box to a human using them. There is a growing interest in explaining the working of these deep models to improve their trustworthiness. In this paper, we introduce a Posthoc Architecture-agnostic Concept Extractor (PACE) that automatically extracts smaller sub-regions of the image called concepts relevant to the black-box prediction. PACE tightly integrates the faithfulness of the explanatory framework to the black-box model. To the best of our knowledge, this is the first work that extracts class-specific discriminative concepts in a posthoc manner automatically. The PACE framework is used to generate explanations for two different CNN architectures trained for classifying the AWA2 and Imagenet-Birds datasets. Extensive human subject experiments are conducted to validate the human interpretability and consistency of the explanations extracted by PACE. The results from these experiments suggest that over 72% of the concepts extracted by PACE are human interpretable.
In text/plain format

Archived Files and Locations

application/pdf  14.9 MB
file_d337q575sfc3dhoe5hbhwczqtq
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-08-31
Version   v1
Language   en ?
arXiv  2108.13828v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 5858a8d4-2428-45df-80dd-a56b5da41285
API URL: JSON