Abstract
Transformers for visual-language representation learning have been getting a lot of interest and shown tremendous performance on visual question answering (VQA) and grounding. However, most systems that show good performance of those tasks still rely on pre-trained object detectors during training, which limits their applicability to the object classes available for those detectors. To mitigate this limitation, this paper focuses on the problem of weakly supervised grounding in the context of visual question answering in transformers. Our approach leverages capsules by transforming each visual token into a capsule representation in the visual encoder; it then uses activations from language self-attention layers as a text-guided selection module to mask those capsules before they are forwarded to the next layer. We evaluate our approach on the challenging GQA as well as VQA-HAT dataset for VQA grounding. Our experiments show that: while removing the information of masked objects from standard transformer architectures leads to a significant drop in performance, the integration of capsules significantly improves the grounding ability of such systems and provides new state-of-the-art results compared to other approaches in the field. (Code is available at https://github.com/aurooj/WSG-VQA-VLTransformers)
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Abacha, A.B., Hasan, S.A., Datla, V.V., Liu, J., Demner-Fushman, D., Müller, H.: VQA-med: overview of the medical visual question answering task at imageclef 2019. (2019)
Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425–2433 (2015)
Arbelle, A., et al.: Detector-free weakly supervised grounding by separation. arXiv preprint arXiv:2104.09829 (2021)
Caron, M., et al.: Emerging properties in self-supervised vision transformers (2021)
Chen, K., Gao, J., Nevatia, R.: Knowledge aided consistency for weakly supervised phrase grounding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4042–4050 (2018)
Chen, Y.C., et al.: Uniter: learning universal image-text representations (2019)
Chen, Z., Ma, L., Luo, W., Wong, K.Y.K.: Weakly-supervised spatio-temporally grounding natural sentence in video. arXiv preprint arXiv:1906.02549 (2019)
Das, A., Agrawal, H., Zitnick, C.L., Parikh, D., Batra, D.: Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions? In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2016)
Datta, S., Sikka, K., Roy, A., Ahuja, K., Parikh, D., Divakaran, A.: Align2ground: weakly supervised phrase grounding guided by image-caption alignment. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2601–2610 (2019)
Desai, K., Johnson, J.: VirTex: learning visual representations from textual annotations. In: CVPR (2021)
Duan, S., Cao, J., Zhao, H.: Capsule-transformer for neural machine translation. arXiv preprint arXiv:2004.14649 (2020)
Duarte, K., Rawat, Y., Shah, M.: Videocapsulenet: a simplified network for action detection. In: Advances in Neural Information Processing Systems, pp. 7610–7619 (2018)
Duarte, K., Rawat, Y.S., Shah, M.: Capsulevos: semi-supervised video object segmentation using capsule routing. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8480–8489 (2019)
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)
Gu, S., Feng, Y.: Improving multi-head attention with capsule networks. In: Tang, J., Kan, MY., Zhao, D., Li, S., Zan, H. (eds.) NLPCC 2019. LNCS (LNAI), vol. 11838, pp. 314–326. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32233-5_25
Gurari, D., et al.: Vizwiz grand challenge: answering visual questions from blind people. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3608–3617 (2018)
Hinton, G.: How to represent part-whole hierarchies in a neural network. arXiv preprint arXiv:2102.12627 (2021)
Hinton, G.E., Krizhevsky, A., Wang, S.D.: Transforming auto-encoders. In: Honkela, T., Duch, W., Girolami, M., Kaski, S. (eds.) ICANN 2011. LNCS, vol. 6791, pp. 44–51. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21735-7_6
Hinton, G.E., Sabour, S., Frosst, N.: Matrix capsules with EM routing. In: International Conference on Learning Representations (2018)
Huang, D.A., Buch, S., Dery, L., Garg, A., Fei-Fei, L., Niebles, J.C.: Finding" it": weakly-supervised reference-aware visual grounding in instructional videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5948–5957 (2018)
Huang, Z., Zeng, Z., Huang, Y., Liu, B., Fu, D., Fu, J.: Seeing out of the box: End-to-end pre-training for vision-language representation learning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)
Huang, Z., Zeng, Z., Liu, B., Fu, D., Fu, J.: Pixel-bert: aligning image pixels with text by deep multi-modal transformers. CoRR abs/2004.00849 (2020). https://arxiv.org/abs/2004.00849
Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. In: International Conference on Learning Representations (ICLR) (2018)
Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Khan, A.U., Kuehne, H., Duarte, K., Gan, C., Lobo, N., Shah, M.: Found a reason for me? weakly-supervised grounded visual question answering using capsules (2021)
Khan, S., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: a survey. arXiv preprint arXiv:2101.01169 (2021)
Kim, W., Son, B., Kim, I.: VILT: vision-and-language transformer without convolution or region supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 5583–5594. PMLR (2021). https://proceedings.mlr.press/v139/kim21k.html
Kim, W., Son, B., Kim, I.: VILT: vision-and-language transformer without convolution or region supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 5583–5594. PMLR (2021). https://proceedings.mlr.press/v139/kim21k.html
Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32–73 (2017)
LaLonde, R., Bagci, U.: Capsules for object segmentation. arXiv preprint arXiv:1804.04241 (2018)
Li, G., Duan, N., Fang, Y., Gong, M., Jiang, D.: Unicoder-vl: a universal encoder for vision and language by cross-modal pre-training. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11336–11344 (2020)
Li, J., Selvaraju, R.R., Gotmare, A.D., Joty, S., Xiong, C., Hoi, S.: Align before fuse: vision and language representation learning with momentum distillation. In: NeurIPS (2021)
Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: Visualbert: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)
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
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Liu, J., et al.: Transformer-based capsule network for stock movement prediction. In: Proceedings of the First Workshop on Financial Technology and Natural Language Processing, pp. 66–73 (2019)
Liu, Y., Wan, B., Ma, L., He, X.: Relation-aware instance refinement for weakly supervised visual grounding. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5612–5621 (2021)
Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. arXiv preprint arXiv:1908.02265 (2019)
Lu, J., Goswami, V., Rohrbach, M., Parikh, D., Lee, S.: 12-in-1: multi-task vision and language representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10437–10446 (2020)
Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. Adv. Neural Inf. Process. Syst. 29 (2016)
Mazzia, V., Salvetti, F., Chiaberge, M.: Efficient-capsnet: capsule network with self-attention routing. arXiv preprint arXiv:2101.12491 (2021)
Miech, A., Alayrac, J.B., Laptev, I., Sivic, J., Zisserman, A.: Thinking fast and slow: efficient text-to-visual retrieval with transformers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9826–9836 (2021)
Mobiny, A., Cicalese, P.A., Nguyen, H.V.: Trans-caps: transformer capsule networks with self-attention routing (2021). https://openreview.net/forum?id=BUPIRa1D2J
Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X.S., Wen, J.R.: Counterfactual VQA: a cause-effect look at language bias. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12700–12710 (2021)
Pfeiffer, J., et al.: XGQA: cross-lingual visual question answering. arXiv preprint arXiv:2109.06082 (2021)
Pucci, R., Micheloni, C., Martinel, N.: Self-attention agreement among capsules. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 272–280 (2021)
Qiao, T., Dong, J., Xu, D.: Exploring human-like attention supervision in visual question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)
Ramakrishnan, S., Agrawal, A., Lee, S.: Overcoming language priors in visual question answering with adversarial regularization. arXiv preprint arXiv:1810.03649 (2018)
Ribeiro, F.D.S., Duarte, K., Everett, M., Leontidis, G., Shah, M.: Learning with capsules: a survey. arXiv preprint arXiv:2206.02664 (2022)
Riquelme, F., De Goyeneche, A., Zhang, Y., Niebles, J.C., Soto, A.: Explaining VQA predictions using visual grounding and a knowledge base. Image Vision Comput. 101, 103968 (2020)
Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: NIPS (2017)
Selvaraju, R.R., et al.: Taking a hint: leveraging explanations to make vision and language models more grounded. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2591–2600 (2019)
Shi, J., Xu, J., Gong, B., Xu, C.: Not all frames are equal: weakly-supervised video grounding with contextual similarity and visual clustering losses. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10444–10452 (2019)
Su, W., et al.: Vl-bert: pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (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 (2019)
Wang, L., Huang, J., Li, Y., Xu, K., Yang, Z., Yu, D.: Improving weakly supervised visual grounding by contrastive knowledge distillation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14090–14100 (2021)
Whitehead, S., Wu, H., Ji, H., Feris, R., Saenko, K.: Separating skills and concepts for novel visual question answering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5632–5641 (2021)
Wu, L., Liu, X., Liu, Q.: Centroid transformers: learning to abstract with attention. arXiv preprint arXiv:2102.08606 (2021)
Xiao, F., Sigal, L., Jae Lee, Y.: Weakly-supervised visual grounding of phrases with linguistic structures. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5945–5954 (2017)
Yang, X., Liu, X., Jian, M., Gao, X., Wang, M.: Weakly-supervised video object grounding by exploring spatio-temporal contexts. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1939–1947 (2020)
Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 21–29 (2016)
Zeng, X., Wang, Y., Chiu, T.Y., Bhattacharya, N., Gurari, D.: Vision skills needed to answer visual questions. Proc. ACM Hum. Comput. Interact. 4(CSCW2), 1–31 (2020)
Zhan, L.M., Liu, B., Fan, L., Chen, J., Wu, X.M.: Medical visual question answering via conditional reasoning. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2345–2354 (2020)
Zhang, J., Bargal, S.A., Lin, Z., Brandt, J., Shen, X., Sclaroff, S.: Top-down neural attention by excitation backprop. Int. J. Comput. Vision 126(10), 1084–1102 (2018)
Zhang, S., Qu, L., You, S., Yang, Z., Zhang, J.: Automatic generation of grounded visual questions. arXiv preprint arXiv:1612.06530 (2016)
Zhang, Y., Niebles, J.C., Soto, A.: Interpretable visual question answering by visual grounding from attention supervision mining. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 349–357 (2019). https://doi.org/10.1109/WACV.2019.00043
Acknowledgement
Aisha Urooj is supported by the ARO grant W911NF-19-1-0356. The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon. Disclaimer: The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of ARO, IARPA, DOI/IBC, or the U.S. Government.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Khan, A.U., Kuehne, H., Gan, C., Lobo, N.D.V., Shah, M. (2022). Weakly Supervised Grounding for VQA in Vision-Language Transformers. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13695. Springer, Cham. https://doi.org/10.1007/978-3-031-19833-5_38
Download citation
DOI: https://doi.org/10.1007/978-3-031-19833-5_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19832-8
Online ISBN: 978-3-031-19833-5
eBook Packages: Computer ScienceComputer Science (R0)