Papers › Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism

Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism

22 Sep 2022arXiv:2209.11189archive 2025-07-28

Ioanna Gkartzonika, Nikolaos Gkalelis, Vasileios Mezaris

In this paper two new learning-based eXplainable AI (XAI) methods for deep convolutional neural network (DCNN) image classifiers, called L-CAM-Fm and L-CAM-Img, are proposed. Both methods use an attention mechanism that is inserted in the original (frozen) DCNN and is trained to derive class activation maps (CAMs) from the last convolutional layer's feature maps. During training, CAMs are applied to the feature maps (L-CAM-Fm) or the input image (L-CAM-Img) forcing the attention mechanism to learn the image regions explaining the DCNN's outcome. Experimental evaluation on ImageNet shows that the proposed methods achieve competitive results while requiring a single forward pass at the inference stage. Moreover, based on the derived explanations a comprehensive qualitative analysis is performed providing valuable insight for understanding the reasons behind classification errors, including possible dataset biases affecting the trained classifier.

PaperPDFCode

Code

bmezaris/l-cam mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Explainable Artificial Intelligence (XAI)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DCNN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections