Abstract
Visual question answer (VQA) grounding, aimed at locating the visual evidence associated with the answers while answering questions, has attracted increasing research interest. To locate the evidence, most existing methods extract attention maps in an unsupervised manner from pretrained VQA models. As only the text-related objective is considered during training, the attention map coarsely depicts the grounding region, resulting in poor interpretability. A straightforward solution for improving grounding accuracy is leveraging pixel-wise masks as strong supervision. However, precise per-pixel annotation is time-consuming and labor-intensive. To address above issues, this paper presents the weakly-supervised grounding for VQA, which learns an end-to-end Dual Visual-Linguistic Interaction (DaVi) network in a unified architecture with various low-cost annotations, such as click-, scribble- and box-level grounding labels. Specifically, to enable the visual mask prediction, DaVi proposes a language-based visual decoder that extends the previous VQA network. Since the visual decoder is guided with weak labels, we also present a Pseudo Grounding Refinement Module (PGRM) to refine the relatively coarse predictions as an additional constraint. Extensive experiments demonstrate that our weakly supervised DaVi significantly improves grounding performance even under the click-level supervision with one pixel annotation. Scribble-level supervision achieves 92% performance at a dramatically reduced annotation cost compared to its fully supervised counterpart. More essentially, weak visual grounding usually boosts the accuracy of text answers despite using inaccurate supervision.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
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)
Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425–2433 (2015)
Chen, C., Anjum, S., Gurari, D.: Grounding answers for visual questions asked by visually impaired people. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 19098–19107 (2022)
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics (2018)
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)
Gurari, D., et al.: Vizwiz-priv: a dataset for recognizing the presence and purpose of private visual information in images taken by blind people. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 939–948 (2019)
Johnson, J., Hariharan, B., Van Der Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.: ClevR: a diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2901–2910 (2017)
Khan, A.U., Kuehne, H., Gan, C., Da Vitoria Lobo, N., Shah, M.: Weakly supervised grounding for VQA in vision-language transformers. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13695, pp. 652–670. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19833-5_38
Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32–73 (2017)
Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML (2022)
Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: Vision and language representation learning with momentum distillation. In: Advances in Neural Information Processing Systems, vol. 34, pp. 9694–9705 (2021)
Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 121–137. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58577-8_8
Loshchilov, I., Hutter, F.: Fixing weight decay regularization in Adam (2017)
Pan, J., et al.: Tell me the evidence? Dual visual-linguistic interaction for answer grounding. arXiv preprint arXiv:2207.05703 (2022)
Ramakrishnan, S.K., Pal, A., Sharma, G., Mittal, A.: An empirical evaluation of visual question answering for novel objects. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4392–4401 (2017)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Schuhmann, C., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models. arXiv preprint arXiv:2210.08402 (2022)
Schuhmann, C., et al.: Laion-400m: open dataset of clip-filtered 400 million image-text pairs. In: NeurIPS Workshop Datacentric AI, number FZJ-2022-00923. Jülich Supercomputing Center (2021)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
Su, H., Jampani, V., Sun, D., Gallo, O., Learned-Miller, E., Kautz, J.: Pixel-adaptive convolutional neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11166–11175 (2019)
Tan, H., Bansal, M.: LxMERT: learning cross-modality encoder representations from transformers. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 5100–5111 (2019)
Urooj, A., Kuehne, H., Duarte, K., Gan, C., Lobo, N., Shah, M.: Found a reason for me? Weakly-supervised grounded visual question answering using capsules. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8465–8474 (2021)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Xu, D., Zhu, Y., Choy, C.B., Fei-Fei, L., Scene graph generation by iterative message passing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5410–5419 (2017)
Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048–2057. PMLR (2015)
Yang, Z., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H.S.: LAVT: language-aware vision transformer for referring image segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 18155–18165 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, Y. et al. (2024). Weakly-Supervised Grounding for VQA with Dual Visual-Linguistic Interaction. In: Fang, L., Pei, J., Zhai, G., Wang, R. (eds) Artificial Intelligence. CICAI 2023. Lecture Notes in Computer Science(), vol 14473. Springer, Singapore. https://doi.org/10.1007/978-981-99-8850-1_13
Download citation
DOI: https://doi.org/10.1007/978-981-99-8850-1_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8849-5
Online ISBN: 978-981-99-8850-1
eBook Packages: Computer ScienceComputer Science (R0)