English

Efficient and Concise Explanations for Object Detection with Gaussian-Class Activation Mapping Explainer

Computer Vision and Pattern Recognition 2024-04-23 v1 Artificial Intelligence

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.

Keywords

Cite

@article{arxiv.2404.13417,
  title  = {Efficient and Concise Explanations for Object Detection with Gaussian-Class Activation Mapping Explainer},
  author = {Quoc Khanh Nguyen and Truong Thanh Hung Nguyen and Vo Thanh Khang Nguyen and Van Binh Truong and Tuong Phan and Hung Cao},
  journal= {arXiv preprint arXiv:2404.13417},
  year   = {2024}
}

Comments

Canadian AI 2024

R2 v1 2026-06-28T16:00:47.354Z