Abstract
The WSDM 2023 Toloka VQA challenge introduces a new Grounding-based Visual Question Answering (GVQA) dataset, elevating multimodal task complexity. This challenge diverges from traditional VQA by requiring models to identify a bounding box in response to an image-question pair, aligning with Visual Grounding tasks. Existing VG approaches, when applied to GVQA, often necessitate external data or larger models for satisfactory results, leading to high computational demands. We approach this as a language modeling problem, utilizing prompt tuning with multiple state-of-the-art VQA models. Our method, operating solely on an NVIDIA RTX3090 GPU without external data, secured third place in the challenge, achieving an Intersection over Union (IoU) of 75.658. Our model notably provides explainability between textual and visual data through its attention mechanism, offering insights into its decision-making process. This research demonstrates that high performance in GVQA can be achieved with minimal resources, enhancing understanding of model dynamics and paving the way for improved interpretability and efficiency. Our code is available here: https://github.com/IKMLab/GViG.git
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chen, T., Saxena, S., Li, L., Fleet, D.J., Hinton, G.: Pix2seq: A language modeling framework for object detection. In: International Conference on Learning Representations (2021)
Dai, Z., Liu, H., Le, Q.V., Tan, M.: CoAtNet: marrying convolution and attention for all data sizes. Adv. Neural. Inf. Process. Syst. 34, 3965–3977 (2021)
Deng, J., Yang, Z., Chen, T., Zhou, W., Li, H.: TransVG: end-to-end visual grounding with transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1769–1779 (2021)
Dosovitskiy, A., et al.: An image is worth 16\(\times \)16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)
Gao, S., Chen, Z., Chen, G., Wang, W., Lu, T.: Champion solution for the WSDM2023 toloka VQA challenge. arXiv preprint arXiv:2301.09045 (2023)
Gao, T., Fisch, A., Chen, D.: Making pre-trained language models better few-shot learners. In: Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021, pp. 3816–3830. Association for Computational Linguistics (ACL) (2021)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Huang, S., et al.: Referring image segmentation via cross-modal progressive comprehension. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10488–10497 (2020)
Jin, W., Cheng, Y., Shen, Y., Chen, W., Ren, X.: A good prompt is worth millions of parameters: low-resource prompt-based learning for vision-language models. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2763–2775 (2022)
Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171–4186 (2019)
Komleva, E.: WSDM2023 VQA. https://github.com/EvgeniaKomleva/WSDM2023_VQA (2023)
Krishna, R., et al.: Visual Genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32–73 (2017). https://doi.org/10.1007/s11263-016-0981-7
Li, C., et al.: mPLUG: effective and efficient vision-language learning by cross-modal skip-connections. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 7241–7259. Association for Computational Linguistics (Dec 2022). https://aclanthology.org/2022.emnlp-main.488
Liu, J., et al.: PolyFormer: referring image segmentation as sequential polygon generation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 18653–18663 (2023)
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., Neubig, G.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 55(9), 1–35 (2023)
Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al.: Improving language understanding by generative pre-training (2018)
Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1715–1725 (2016)
Tsimpoukelli, M., Menick, J.L., Cabi, S., Eslami, S., Vinyals, O., Hill, F.: Multimodal few-shot learning with frozen language models. Adv. Neural. Inf. Process. Syst. 34, 200–212 (2021)
Ustalov, D., Pavlichenko, N., Likhobaba, D., Smirnova, A.: WSDM cup 2023 challenge on visual question answering (2023)
Vaswani, A., et al.: Attention is all you need. In: Advances in neural information processing systems, vol. 30 (2017)
Wang, P., et al.: OFA: unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In: International Conference on Machine Learning, pp. 23318–23340. PMLR (2022)
Yang, Z., Gong, B., Wang, L., Huang, W., Yu, D., Luo, J.: A fast and accurate one-stage approach to visual grounding. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4683–4693 (2019)
Zhang, H., Wong, K.: VQA. https://github.com/Hyu-Zhang/VQA (2023)
Acknowledgement
This work was supported by the National Science and Technology Council, Taiwan, under Grant NSTC 112-2223-E-006-009.
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
Li, YT., Lin, YJ., Yeh, CJ., Lin, CY., Kao, HY. (2024). GViG: Generative Visual Grounding Using Prompt-Based Language Modeling for Visual Question Answering. In: Yang, DN., Xie, X., Tseng, V.S., Pei, J., Huang, JW., Lin, J.CW. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2024. Lecture Notes in Computer Science(), vol 14650. Springer, Singapore. https://doi.org/10.1007/978-981-97-2266-2_7
Download citation
DOI: https://doi.org/10.1007/978-981-97-2266-2_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2265-5
Online ISBN: 978-981-97-2266-2
eBook Packages: Computer ScienceComputer Science (R0)