GRACE: Graph-Based Contextual Debiasing for Fair Visual Question Answering | SpringerLink
Skip to main content
Springer Nature Link
Log in

GRACE: Graph-Based Contextual Debiasing for Fair Visual Question Answering

  • Conference paper
  • First Online:
Computer Vision – ECCV 2024 (ECCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15075))

Included in the following conference series:

  • 18 Accesses

Abstract

Large language models (LLMs) exhibit exceptional reasoning capabilities and have played significant roles in knowledge-based visual question-answering (VQA) systems. By conditioning on in-context examples and task-specific prompts, they comprehensively understand input questions and provide answers relevant to the context. However, due to the reliance on in-context examples, LLMs are susceptible to inheriting dataset biases in context descriptions and the provided examples. Innovative methods are required to ensure that LLMs can deliver unbiased yet contextually relevant responses. To tackle this challenge, we present GRAph-based Contextual DEbiasing (GRACE), a novel graph-based method for debiasing knowledge-based VQA models. This approach consists of two novel and generally applicable components. First, we propose an unsupervised context graph learning method that combats biases by explicitly creating a balanced context graph under the guidance of fairness constraints. Second, building upon the context graph, we consider both semantic features and reasoning processes to enhance prompting with more relevant and diverse in-context examples. Through extensive experimentation on both in-distribution (OK-VQA) and out-of-distribution (VQA-CP, GQA-OOD) datasets, we demonstrate the effectiveness of GRACE in mitigating biases and achieving generalization. Additionally, analyses of the model performance across gender groups demonstrate GRACE’s potential impacts on social equity. Our source code is publicly available at https://github.com/SuperJohnZhang/ContextGraphKVQA.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 8007
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 10009
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Agrawal, A., Batra, D., Parikh, D., Kembhavi, A.: Don’t just assume; look and answer: overcoming priors for visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4971–4980 (2018)

    Google Scholar 

  2. Alvi, M., Zisserman, A., Nellåker, C.: Turning a blind eye: explicit removal of biases and variation from deep neural network embeddings. In: Proceedings of the European Conference on Computer Vision Workshops (2018)

    Google Scholar 

  3. Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6077–6086 (2018)

    Google Scholar 

  4. Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 39–48 (2016)

    Google Scholar 

  5. Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425–2433 (2015)

    Google Scholar 

  6. Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877–1901 (2020)

    Google Scholar 

  7. Caliskan, A., Bryson, J.J., Narayanan, A.: Semantics derived automatically from language corpora contain human-like biases. Science 356(6334), 183–186 (2017)

    Article  Google Scholar 

  8. Caton, S., Haas, C.: Fairness in machine learning: a survey. ACM Comput. Surv. (2020)

    Google Scholar 

  9. Chen, L., Yan, X., Xiao, J., Zhang, H., Pu, S., Zhuang, Y.: Counterfactual samples synthesizing for robust visual question answering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)

    Google Scholar 

  10. Chen, S., Jin, Q., Wang, P., Wu, Q.: Say as you wish: fine-grained control of image caption generation with abstract scene graphs. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9962–9971 (2020)

    Google Scholar 

  11. Chen, W., Gan, Z., Li, L., Cheng, Y., Wang, W., Liu, J.: Meta module network for compositional visual reasoning. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 655–664 (2021)

    Google Scholar 

  12. Clark, C., Yatskar, M., Zettlemoyer, L.: Don’t take the easy way out: ensemble based methods for avoiding known dataset biases. arXiv preprint arXiv:1909.03683 (2019)

  13. Dong, Y., Ma, J., Wang, S., Chen, C., Li, J.: Fairness in graph mining: a survey. IEEE Trans. Knowl. Data Eng. (2023)

    Google Scholar 

  14. Elkan, C.: The foundations of cost-sensitive learning. In: International Joint Conference on Artificial Intelligence, vol. 17, pp. 973–978. Lawrence Erlbaum Associates Ltd. (2001)

    Google Scholar 

  15. Fu, X., Zhang, J., Meng, Z., King, I.: MAGNN: metapath aggregated graph neural network for heterogeneous graph embedding. In: Proceedings of The Web Conference 2020, pp. 2331–2341 (2020)

    Google Scholar 

  16. Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. arXiv preprint arXiv:1606.01847 (2016)

  17. Gardères, F., Ziaeefard, M., Abeloos, B., Lecue, F.: ConceptBERT: concept-aware representation for visual question answering. In: Proceedings of the Empirical Methods in Natural Language Processing, pp. 489–498 (2020)

    Google Scholar 

  18. Gebru, T., et al.: Datasheets for datasets. Commun. ACM 64(12), 86–92 (2021)

    Article  Google Scholar 

  19. Givens, C.R., Shortt, R.M.: A class of Wasserstein metrics for probability distributions. Mich. Math. J. 31(2), 231–240 (1984)

    Article  MathSciNet  Google Scholar 

  20. Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: Elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904–6913 (2017)

    Google Scholar 

  21. Gu, J., Zhao, H., Lin, Z., Li, S., Cai, J., Ling, M.: Scene graph generation with external knowledge and image reconstruction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1969–1978 (2019)

    Google Scholar 

  22. Gui, L., Wang, B., Huang, Q., Hauptmann, A., Bisk, Y., Gao, J.: Kat: A knowledge augmented transformer for vision-and-language. arXiv preprint arXiv:2112.08614 (2021)

  23. Gupta, N., Lin, K., Roth, D., Singh, S., Gardner, M.: Neural module networks for reasoning over text. arXiv preprint arXiv:1912.04971 (2019)

  24. Han, X., Wang, S., Su, C., Huang, Q., Tian, Q.: General greedy de-bias learning. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 9789–9805 (2023)

    Article  Google Scholar 

  25. Hendricks, L.A., Burns, K., Saenko, K., Darrell, T., Rohrbach, A.: Women also Snowboard: overcoming bias in captioning models. In: Proceedings of the European Conference on Computer Vision, pp. 771–787 (2018)

    Google Scholar 

  26. Hessel, J., et al.: The abduction of sherlock Holmes: a dataset for visual abductive reasoning. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) European Conference on Computer Vision, pp. 558–575. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20059-5_32

  27. Hu, R., Andreas, J., Darrell, T., Saenko, K.: Explainable neural computation via stack neural module networks. IEEE Trans., 53–69 (2018)

    Google Scholar 

  28. Hu, X., et al.: Discovering biases in image datasets with the crowd. In: Proceedings of HCOMP (2019)

    Google Scholar 

  29. Hu, Y., Hua, H., Yang, Z., Shi, W., Smith, N.A., Luo, J.: PromptCap: prompt-guided task-aware image captioning. arXiv preprint arXiv:2211.09699 (2022)

  30. Hudson, D., Manning, C.D.: Learning by abstraction: the neural state machine. In: Advances in Neural Information Processing Systems, vol. 32 (2019)

    Google Scholar 

  31. Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. arXiv preprint arXiv:1803.03067 (2018)

  32. Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700–6709 (2019)

    Google Scholar 

  33. Jeh, G., Widom, J.: SimRank: a measure of structural-context similarity. In: Proceedings of the eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 538–543 (2002)

    Google Scholar 

  34. Kervadec, C., Antipov, G., Baccouche, M., Wolf, C.: Roses are red, violets are blue... but should VQA expect them to? In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2776–2785 (2021)

    Google Scholar 

  35. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2017)

    Google Scholar 

  36. Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)

  37. Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. Adv. Neural. Inf. Process. Syst. 35, 22199–22213 (2022)

    Google Scholar 

  38. Lin, Y., Xie, Y., Chen, D., Xu, Y., Zhu, C., Yuan, L.: REVIVE: regional visual representation matters in knowledge-based visual question answering. arXiv preprint arXiv:2206.01201 (2022)

  39. Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)

    Google Scholar 

  40. Locatello, F., Abbati, G., Rainforth, T., Bauer, S., Schölkopf, B., Bachem, O.: On the fairness of disentangled representations. In: Advances in Neural Information Processing Systems, vol. 32 (2019)

    Google Scholar 

  41. Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: OK-VQA: a visual question answering benchmark requiring external knowledge. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3195–3204 (2019)

    Google Scholar 

  42. Merity, S., Xiong, C., Bradbury, J., Socher, R.: Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843 (2016)

  43. Park, S., Hwang, S., Hong, J., Byun, H.: Fair-VQA: fairness-aware visual question answering through sensitive attribute prediction. IEEE Access 8, 215091–215099 (2020)

    Article  Google Scholar 

  44. Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: FiLM: visual reasoning with a general conditioning layer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)

    Google Scholar 

  45. Pu, Y., Gan, Z., Henao, R., Yuan, X., Li, C., Stevens, A., Carin, L.: Variational autoencoder for deep learning of images, labels and captions. In: Advances in Neural Information Processing Systems, vol. 29 (2016)

    Google Scholar 

  46. Ryu, H.J., Adam, H., Mitchell, M.: InclusiveFaceNet: improving face attribute detection with race and gender diversity. arXiv preprint arXiv:1712.00193 (2017)

  47. Santoro, A., et al.: A simple neural network module for relational reasoning. In: Proceedings of the Conference and Workshop on Neural Information Processing Systems, pp. 4967–4976 (2017)

    Google Scholar 

  48. Shao, Z., Yu, Z., Wang, M., Yu, J.: Prompting large language models with answer heuristics for knowledge-based visual question answering. In: Computer Vision and Pattern Recognition (CVPR), pp. 14974–14983 (2023)

    Google Scholar 

  49. Shi, J., Zhang, H., Li, J.: Explainable and explicit visual reasoning over scene graphs. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8376–8384 (2019)

    Google Scholar 

  50. Simpson, E.H.: Measurement of diversity. Nature 163(4148), 688–688 (1949)

    Article  Google Scholar 

  51. Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)

  52. Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)

  53. Touvron, H., et al.: LLaMA 2: open foundation and fine-tuned chat models (2023)

    Google Scholar 

  54. Tzeng, E., Hoffman, J., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4068–4076 (2015)

    Google Scholar 

  55. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)

  56. Verma, S., Rubin, J.: Fairness definitions explained. In: Proceedings of the International Workshop on Software Fairness, pp. 1–7 (2018)

    Google Scholar 

  57. Wang, A., et al.: REVISE: a tool for measuring and mitigating bias in visual datasets. Int. J. Comput. Vis. 130(7), 1790–1810 (2022). https://doi.org/10.1007/s11263-022-01625-5

    Article  Google Scholar 

  58. Wang, P., Wu, Q., Shen, C., Dick, A., Van Den Hengel, A.: FVQA: fact-based visual question answering. IEEE Trans. Pattern Anal. Mach. Intell. 40(10), 2413–2427 (2017)

    Article  Google Scholar 

  59. Wu, J., Lu, J., Sabharwal, A., Mottaghi, R.: Multi-modal answer validation for knowledge-based VQA. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 2712–2721 (2022)

    Google Scholar 

  60. Xiong, C., Merity, S., Socher, R.: Dynamic memory networks for visual and textual question answering. In: International Conference on Machine Learning, pp. 2397–2406. PMLR (2016)

    Google Scholar 

  61. Xu, H., Saenko, K.: Ask, Attend and Answer: exploring question-guided spatial attention for visual question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 451–466. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_28

    Chapter  Google Scholar 

  62. Yang, Z., et al.: An empirical study of GPT-3 for few-shot knowledge-based VQA. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 3081–3089 (2022)

    Google Scholar 

  63. Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 21–29 (2016)

    Google Scholar 

  64. Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: CVPR, pp. 6713–6724 (2019)

    Google Scholar 

  65. Zhang, B.H., Lemoine, B., Mitchell, M.: Mitigating unwanted biases with adversarial learning. In: Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, pp. 335–340 (2018)

    Google Scholar 

  66. Zhang, P., et al.: VinVL: revisiting visual representations in vision-language models. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5579–5588 (2021)

    Google Scholar 

  67. Zhang, Y., Jiang, M., Zhao, Q.: Explicit knowledge incorporation for visual reasoning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1356–1365 (2021)

    Google Scholar 

  68. Zhang, Y., Jiang, M., Zhao, Q.: Query and attention augmentation for knowledge-based explainable reasoning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 15576–15585 (2022)

    Google Scholar 

  69. Zhu, B., Niu, Y., Lee, S., Hur, M., Zhang, H.: Debiased fine-tuning for vision-language models by prompt regularization. arXiv preprint arXiv:2301.12429 (2023)

Download references

Acknowledgment

This work is supported by NSF Grants 2143197 and 2227450.

Author information

Authors and Affiliations

  1. University of Minnesota, Minneapolis, MN, 55455, USA

    Yifeng Zhang, Ming Jiang & Qi Zhao

Authors
  1. Yifeng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ming Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Qi Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yifeng Zhang .

Editor information

Editors and Affiliations

  1. University of Birmingham, Birmingham, UK

    Aleš Leonardis

  2. University of Trento, Trento, Italy

    Elisa Ricci

  3. Technical University of Darmstadt, Darmstadt, Germany

    Stefan Roth

  4. Princeton University, Princeton, NJ, USA

    Olga Russakovsky

  5. Czech Technical University in Prague, Prague, Czech Republic

    Torsten Sattler

  6. École des Ponts ParisTech, Marne-la-Vallée, France

    Gül Varol

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 868 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Zhang, Y., Jiang, M., Zhao, Q. (2025). GRACE: Graph-Based Contextual Debiasing for Fair Visual Question Answering. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15075. Springer, Cham. https://doi.org/10.1007/978-3-031-72643-9_11

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-72643-9_11

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-72642-2

  • Online ISBN: 978-3-031-72643-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation