G-CAME: Gaussian-Class Activation Mapping Explainer for Object Detectors

Quoc Khanh Nguyen, Truong Thanh Hung Nguyen, Vo Thanh Khang Nguyen, Van Binh Truong, Quoc Hung Cao
6/6/2023
cs.CVcs.AIcs.LG

No official code found. Best implementation: khanhnguyenuet/GCAME (3 stars, CC0-1.0, last commit 2022-11-22).

Abstract

Nowadays, deep neural networks for object detection in images are very prevalent. However, due to the complexity of these networks, users find it hard to understand why these objects are detected by models. We proposed Gaussian Class Activation Mapping Explainer (G-CAME), which generates a saliency map as the explanation for object detection models. G-CAME can be considered a CAM-based method that uses the activation maps of selected layers combined with the Gaussian kernel to highlight the important regions in the image for the predicted box. Compared with other Region-based methods, G-CAME can transcend time constraints as it takes a very short time to explain an object. We also evaluated our method qualitatively and quantitatively with YOLOX on the MS-COCO 2017 dataset and guided to apply G-CAME into the two-stage Faster-RCNN model.

View on arXivView PDF

Code Implementations(1)

khanhnguyenuet/GCAMECommunity100%
CC0-1.0

Gaussian Class Activation Mapping Explainer implementation in Pytorch

30Python, Jupyter NotebookNov 22, 20223 years agoCC0-1.0

Similar Papers

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

92% match1 repo32024

Towards Better Explanations for Object Detection

87% match1 repo112023

ODSmoothGrad: Generating Saliency Maps for Object Detectors

87% match2023

SSD: Single Shot MultiBox Detector

86% match1 repo4.8k2015

Leveraging Activations for Superpixel Explanations

86% match2024

KPCA-CAM: Visual Explainability of Deep Computer Vision Models using Kernel PCA

86% match1 repo12.9k2024

Cite this paper

@article{nguyen2023gcame,
  title  = {G-CAME: Gaussian-Class Activation Mapping Explainer for Object Detectors},
  author = {Quoc Khanh Nguyen and Truong Thanh Hung Nguyen and Vo Thanh Khang Nguyen and Van Binh Truong and Quoc Hung Cao},
  year   = {2023},
  eprint = {2306.03400},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.03400v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.03400.svg)](https://codeofpaper.com/paper/2306.03400)

Discussion