Efficient and Concise Explanations for Object Detection with Gaussian-Class Activation Mapping Explainer
Year: 2024
Type: preprint
Abstract: To address the challenges of providing quick and plausible explanations in Explainable AI (XAI) for object detection models, we introduce the Gaussian Class Activation Mapping Explainer (G-CAME). Our method efficiently generates concise saliency maps by utilizing activation maps from selected layers and applying a Gaussian kernel to emphasize critical image regions for the predicted object. Compared with other Region-based approaches, G-CAME significantly reduces explanation time to 0.5 seconds without compromising the quality. Our evaluation of G-CAME, using Faster-RCNN and YOLOX on the MS-COCO 2017 dataset, demonstrates its ability to offer highly plausible and faithful explanations, especially in reducing the bias on tiny object detection.
Source: arXiv (Cornell University)
Authors: Nguyen, Quoc Khanh, Nguyen, Truong Thanh Hung, Nguyen, Vo Thanh Khang, Truong, Van Binh, Phan, Tuong, Cao, Hung
Institutions: University of Waterloo, University of New Brunswick
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4395065003