Black-box Explanation of Object Detectors via Saliency Maps

We propose D-RISE, a method for generating visual explanations for the predictions of object detectors. Utilizing the proposed similarity metric that accounts for both localization and categorization aspects of object detection allows our method to produce saliency maps that show image areas that mo...

Full description

Saved in:
Bibliographic Details
Published in2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 11438 - 11447
Main Authors Petsiuk, Vitali, Jain, Rajiv, Manjunatha, Varun, Morariu, Vlad I., Mehra, Ashutosh, Ordonez, Vicente, Saenko, Kate
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2021
Subjects
Computational modeling
Error analysis
Location awareness
Measurement
Pathology
Software testing
Visualization
Online AccessGet full text

Cover

More Information
Summary:We propose D-RISE, a method for generating visual explanations for the predictions of object detectors. Utilizing the proposed similarity metric that accounts for both localization and categorization aspects of object detection allows our method to produce saliency maps that show image areas that most affect the prediction. D-RISE can be considered "black-box" in the software testing sense, as it only needs access to the inputs and outputs of an object detector. Compared to gradient-based methods, D-RISE is more general and agnostic to the particular type of object detector being tested, and does not need knowledge of the inner workings of the model. We show that D-RISE can be easily applied to different object detectors including one-stage detectors such as YOLOv3 and two-stage detectors such as Faster-RCNN. We present a detailed analysis of the generated visual explanations to highlight the utilization of context and possible biases learned by object detectors.
ISSN:2575-7075
DOI:10.1109/CVPR46437.2021.01128