• Home
  • Search
  • Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects
  • Open Access IconOpen Access
  • Cite Icon90
  • https://doi.org/10.18653/v1/w19-1801Copy DOI Icon

Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects

  • Jan 1, 2019
  • Gabriel Grand +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Visual question answering (VQA) models have been shown to over-rely on linguistic biases in VQA datasets, answering questions "blindly" without considering visual context. Adversarial regularization (AdvReg) aims to address this issue via an adversary subnetwork that encourages the main model to learn a bias-free representation of the question. In this work, we investigate the strengths and shortcomings of AdvReg with the goal of better understanding how it affects inference in VQA models. Despite achieving a new stateof-the-art on VQA-CP, we find that AdvReg yields several undesirable side-effects, including unstable gradients and sharply reduced performance on in-domain examples. We demonstrate that gradual introduction of regularization during training helps to alleviate, but not completely solve, these issues. Through error analyses, we observe that AdvReg improves generalization to binary questions, but impairs performance on questions with heterogeneous answer distributions. Qualitatively, we also find that regularized models tend to over-rely on visual features, while ignoring important linguistic cues in the question. Our results suggest that AdvReg requires further refinement before it can be considered a viable bias mitigation technique for VQA.

Similar Papers
  • Research Article
  • Citations42

Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding.

  • Jan 01, 2021
  • IEEE Transactions on Neural Networks and Learning Systems
  • Qingxing Cao +4
  • PDF
  • Conference Article
  • Citations2

Can Pre-training help VQA with Lexical Variations?

  • Jan 01, 2020
  • Shailza Jolly +1
  • Research Article
  • Citations503

Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering

  • Sep 11, 2018
  • International Journal of Computer Vision
  • Yash Goyal +5
  • Research Article
  • Citations1

Adversarial Sample Synthesis for Visual Question Answering

  • Nov 21, 2024
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Chuanhao Li +4
  • Conference Article
  • Citations668

Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering

  • Jun 01, 2018
  • Aishwarya Agrawal +3
  • PDF
  • Research Article
  • Citations19

Advancing surgical VQA with scene graph knowledge

  • May 23, 2024
  • International Journal of Computer Assisted Radiology and Surgery
  • Kun Yuan +5
  • Video Transcripts

Question Agnostic Attention for Visual Question Answering

  • Dec 29, 2020
  • Underline Science Inc.
  • Moshiur Farazi
  • Conference Article
  • Citations10

Question-Agnostic Attention for Visual Question Answering

  • Jan 10, 2021
  • Moshiur Farazi +2
  • Research Article

Visual Question Answering Model Using Transformer-Based Multi-Head Cross Attention Network with Optimized Gold Rush Octave Convolution Network

  • Oct 28, 2025
  • International Journal of Image and Graphics
  • J Jinu Sophia +2
  • Conference Article

Estimation of Visual Contents from Human Brain Signals via VQA Based on Brain-Specific Attention

  • Jun 04, 2023
  • Ryo Shichida +4
  • Conference Article
  • Citations15

Feature Enhancement in Attention for Visual Question Answering

  • Jul 01, 2018
  • Yuetan Lin +3
  • Conference Article
  • Citations47

Quantifying and Alleviating the Language Prior Problem in Visual Question Answering

  • Jul 18, 2019
  • Yangyang Guo +5
  • Research Article
  • Citations8

Parallel multi-head attention and term-weighted question embedding for medical visual question answering.

  • Mar 11, 2023
  • Multimedia Tools and Applications
  • Sruthy Manmadhan +1
  • Conference Article
  • Citations3

NLP Meets Vision for Visual Interpretation - A Retrospective Insight and Future directions

  • May 20, 2021
  • Ahmed Jamshed +1
  • Research Article
  • Citations20

A framework for visual question answering with the integration of scene-text using PHOCs and fisher vectors

  • Nov 07, 2021
  • Expert Systems with Applications
  • Himanshu Sharma +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.