DExT: Detector Explanation Toolkit
- State-of-the-art object detectors are treated as black boxes due to their highly non-linear internal computations. Even with unprecedented advancements in detector performance, the inability to explain how their outputs are generated limits their use in safety-critical applications. Previous work fails to produce explanations for both bounding box and classification decisions, and generally make individual explanations for various detectors. In this paper, we propose an open-source Detector Explanation Toolkit (DExT) which implements the proposed approach to generate a holistic explanation for all detector decisions using certain gradient-based explanation methods. We suggests various multi-object visualization methods to merge the explanations of multiple objects detected in an image as well as the corresponding detections in a single image. The quantitative evaluation show that the Single Shot MultiBox Detector (SSD) is more faithfully explained compared to other detectors regardless of the explanation methods. Both quantitative and human-centric evaluations identify that SmoothGrad with Guided Backpropagation (GBP) provides more trustworthy explanations among selected methods across all detectors. We expect that DExT will motivate practitioners to evaluate object detectors from the interpretability perspective by explaining both bounding box and classification decisions. 21 pages, with supplementary
Document Type: | Preprint |
---|---|
Language: | English |
Author: | Deepan Chakravarthi Padmanabhan, Matias Valdenegro-Toro |
Number of pages: | 21 |
DOI: | https://doi.org/10.48550/arXiv.2212.11409 |
Publisher: | arXiv |
Date of first publication: | 2022/12/21 |
Departments, institutes and facilities: | Fachbereich Informatik |
Dewey Decimal Classification (DDC): | 0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik |
Entry in this database: | 2023/01/04 |