ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2103.14712
6
4

Generating and Evaluating Explanations of Attended and Error-Inducing Input Regions for VQA Models

26 March 2021
Arijit Ray
Michael Cogswell
Xiaoyu Lin
Kamran Alipour
Ajay Divakaran
Yi Yao
Giedrius Burachas
    FAtt
ArXivPDFHTML
Abstract

Attention maps, a popular heatmap-based explanation method for Visual Question Answering (VQA), are supposed to help users understand the model by highlighting portions of the image/question used by the model to infer answers. However, we see that users are often misled by current attention map visualizations that point to relevant regions despite the model producing an incorrect answer. Hence, we propose Error Maps that clarify the error by highlighting image regions where the model is prone to err. Error maps can indicate when a correctly attended region may be processed incorrectly leading to an incorrect answer, and hence, improve users' understanding of those cases. To evaluate our new explanations, we further introduce a metric that simulates users' interpretation of explanations to evaluate their potential helpfulness to understand model correctness. We finally conduct user studies to see that our new explanations help users understand model correctness better than baselines by an expected 30\% and that our proxy helpfulness metrics correlate strongly (ρ>0.97\rho>0.97ρ>0.97) with how well users can predict model correctness.

View on arXiv
Comments on this paper