paper-with-me

홈 › Papers

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

2022-09-22 · 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.

📄 PDF Abstract BibTeX arXiv:2209.11189

Code (1)

bmezaris/l-cam pytorch

Tasks

Explainable Artificial Intelligence (XAI)

Methods 이 논문이 사용한 방법론

DCNN Diffusion-convolutional neural networks (DCNN) is a model for graph-structured data. Through the introduction of a diffusion-convolution operation, diffusion-based representations…

Similar Papers 제목 키워드 기반

Towards Counterfactual and Contrastive Explainability and Transparency of DCNN Image Classifiers

2025-01-12 · SYED ALI TARIQ, Tehseen Zia, MUBEEN GHAFOOR

Explainability of deep convolutional neural networks (DCNNs) is an important research topic that tries to uncover the reasons behind a DCNN model's decisions and improve their understanding and reliability in high-risk e…

counterfactual

Deep adversarial attack on target detection systems

2021-08-12 · Uche M. Osahor, Nasser M. Nasrabadi

Target detection systems identify targets by localizing their coordinates on the input image of interest. This is ideally achieved by labeling each pixel in an image as a background or a potential target pixel. Deep Conv…

Adversarial Attack

The Costs and Benefits of Goal-Directed Attention in Deep Convolutional Neural Networks

2020-02-06 · Xiaoliang Luo, Brett D. Roads, Bradley C. Love

People deploy top-down, goal-directed attention to accomplish tasks, such as finding lost keys. By tuning the visual system to relevant information sources, object recognition can become more efficient (a benefit) and mo…

Object RecognitionTransfer Learning

Deep Convolutional Neural Network Features and the Original Image

2016-11-06 · Connor J. Parde, Carlos Castillo, Matthew Q. Hill, Y. Ivette Colon 외

Face recognition algorithms based on deep convolutional neural networks (DCNNs) have made progress on the task of recognizing faces in unconstrained viewing conditions. These networks operate with compact feature-based f…

Face Recognition

DiG-IN: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations

2024-01-01 · CVPR 2024 1 · Maximilian Augustin, Yannic Neuhaus, Matthias Hein

While deep learning has led to huge progress in complex image classification tasks like ImageNet unexpected failure modes e.g. via spurious features call into question how reliably these classifiers work in the wild.…

counterfactualimage-classificationImage ClassificationImage Generation