mlsanityData to 14 Oct 2026

Faithful Attention Explainer: Verbalizing Decisions Based on Discriminative Features

arXiv 2405.13032 ↗First posted 16 May 2024cs.CL cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In recent years, model explanation methods have been designed to interpret model decisions faithfully and intuitively so that users can easily understand them. In this paper, we propose a framework, Faithful Attention Explainer (FAE), capable of generating faithful textual explanations regarding the attended-to features. Towards this goal, we deploy an attention module that takes the visual feature maps from the classifier for sentence generation. Furthermore, our method successfully learns the association between features and words, which allows a novel attention enforcement module for attention explanation. Our model achieves promising performance in caption quality metrics and a faithful decision-relevance metric on two datasets (CUB and ACT-X). In addition, we show that FAE can interpret gaze-based human attention, as human gaze indicates the discriminative features that humans use for decision-making, demonstrating the potential of deploying human gaze for advanced human-AI interaction.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 29 references that are in the map. First posted on arXiv 16 May 2024.

Builds on

23 of 29 references.

References · 23

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  3. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  4. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
  5. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
  6. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 404
  7. 2016Image Captioning with Semantic Attentioncited by 260
  8. 2016Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioningcited by 232
  9. 2018Textual Explanations for Self-Driving Vehiclescited by 226
  10. 2016SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioningcited by 219
  11. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  12. 2018Multimodal Explanations: Justifying Decisions and Pointing to the Evidencecited by 179
11 more
  1. 2016Generating Visual Explanationscited by 158
  2. 2016Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?cited by 111
  3. 2022A Consistent and Efficient Evaluation Strategy for Attribution Methodscited by 102
  4. 2022Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanationscited by 85
  5. 2018Grounded Video Descriptioncited by 78
  6. 2020Interpreting Chest X-rays via CNNs that Exploit Hierarchical Disease Dependencies and Uncertainty Labelscited by 56
  7. 2016Attention Correctness in Neural Image Captioningcited by 35
  8. 2021Human Attention in Fine-grained Classificationcited by 21
  9. 2022Prophet Attention: Predicting Attention with Future Attention for Image Captioningcited by 10
  10. 2017InterpNET: Neural Introspection for Interpretable Deep Learningcited by 5
  11. 2022User Trust on an Explainable AI-based Medical Diagnosis Support Systemcited by 2

Built on by

Not cited yet.