mlsanityData to 14 Oct 2026

Language bias in Visual Question Answering: A Survey and Taxonomy

arXiv 2111.08531 ↗First posted 16 Nov 2021cs.CV cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Visual question answering (VQA) is a challenging task, which has attracted more and more attention in the field of computer vision and natural language processing. However, the current visual question answering has the problem of language bias, which reduces the robustness of the model and has an adverse impact on the practical application of visual question answering. In this paper, we conduct a comprehensive review and analysis of this field for the first time, and classify the existing methods according to three categories, including enhancing visual information, weakening language priors, data enhancement and training strategies. At the same time, the relevant representative methods are introduced, summarized and analyzed in turn. The causes of language bias are revealed and classified. Secondly, this paper introduces the datasets mainly used for testing, and reports the experimental results of various existing methods. Finally, we discuss the possible future research directions in this field.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 51 of its 109 references that are in the map. First posted on arXiv 16 Nov 2021.

Builds on

51 of 109 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2017Mask R-CNNcited by 7,277
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  6. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  7. 2015VQA: Visual Question Answeringcited by 2,506
  8. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,553
  9. 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,312
  10. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,143
  11. 2019OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledgecited by 1,121
  12. 2020Long-tail learning via logit adjustmentcited by 618
38 more
  1. 2016Neural Architectures for Named Entity Recognitioncited by 550
  2. 2017Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answeringcited by 339
  3. 2019Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biasescited by 280
  4. 2015Stacked Attention Networks for Image Question Answeringcited by 273
  5. 2020Counterfactual VQA: A Cause-Effect Look at Language Biascited by 266
  6. 2019DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversationcited by 186
  7. 2019RUBi: Reducing Unimodal Biases in Visual Question Answeringcited by 185
  8. 2020Counterfactual Samples Synthesizing for Robust Visual Question Answeringcited by 153
  9. 2019Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Groundedcited by 128
  10. 2019Relation-Aware Graph Attention Network for Visual Question Answeringcited by 119
  11. 2019Learning by Abstraction: The Neural State Machinecited by 113
  12. 2018Overcoming Language Priors in Visual Question Answering with Adversarial Regularizationcited by 105
  13. 2020On the Value of Out-of-Distribution Testing: An Example of Goodhart's Lawcited by 74
  14. 2019MUREL: Multimodal Relational Reasoning for Visual Question Answeringcited by 68
  15. 2020Learning What Makes a Difference from Counterfactual Examples and Gradient Supervisioncited by 66
  16. 2020MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answeringcited by 63
  17. 2019Self-Critical Reasoning for Robust Visual Question Answeringcited by 61
  18. 2020Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropiescited by 57
  19. 2016Factors in Finetuning Deep Model for object detectioncited by 53
  20. 2020Overcoming Language Priors with Self-supervised Learning for Visual Question Answeringcited by 43
  21. 2020Unshuffling Data for Improved Generalizationcited by 35
  22. 2020Reducing Language Biases in Visual Question Answering with Visually-Grounded Question Encodercited by 34
  23. 2021Greedy Gradient Ensemble for Robust Visual Question Answeringcited by 34
  24. 2019Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effectscited by 25
  25. 2020WeaQA: Weak Supervision via Captions for Visual Question Answeringcited by 25
  26. 2019Subjective and Objective De-raining Quality Assessment Towards Authentic Rain Imagecited by 18
  27. 2020Visual Grounding Methods for VQA are Working for the Wrong Reasons!cited by 18
  28. 2021AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Losscited by 18
  29. 2021Check It Again: Progressive Visual Question Answering via Visual Entailmentcited by 18
  30. 2021LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question Answeringcited by 17
  31. 2020Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embeddingcited by 16
  32. 2019A New Local Transformation Module for Few-shot Segmentationcited by 15
  33. 2021X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answeringcited by 10
  34. 2019Actively Seeking and Learning from Live Datacited by 9
  35. 2020Learning content and context with language bias for Visual Question Answeringcited by 7
  36. 2021Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoningcited by 6
  37. 2019A New Few-shot Segmentation Network Based on Class Representationcited by 4
  38. 2021A Picture May Be Worth a Hundred Words for Visual Question Answeringcited by 3

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2; 2024: 2.

6 papers.

  1. 2022From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Modelscited by 115
  2. 2022All You May Need for VQA are Image Captionscited by 65
  3. 2023From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunitiescited by 25
  4. 2024CIC: A Framework for Culturally-Aware Image Captioningcited by 8
  5. 2024Understanding Museum Exhibits using Vision-Language Reasoningcited by 4
  6. 2023Overcoming Language Bias in Remote Sensing Visual Question Answering via Adversarial Trainingcited by 1