Abstract
Prior work in visual dialog has focused on training deep neural models on VisDial in isolation. Instead, we present an approach to leverage pretraining on related vision-language datasets before transferring to visual dialog. We adapt the recently proposed ViLBERT model for multi-turn visually-grounded conversations. Our model is pretrained on the Conceptual Captions and Visual Question Answering datasets, and finetuned on VisDial. Our best single model outperforms prior published work by \(1\%\) absolute on NDCG and MRR.
Next, we find that additional finetuning using “dense” annotations in VisDial leads to even higher NDCG – more than \(10\%\) over our base model – but hurts MRR – more than \(17\%\) below our base model! This highlights a trade-off between the two primary metrics – NDCG and MRR – which we find is due to dense annotations not correlating well with the original ground-truth answers to questions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Publicly available on visualdialog.org/data.
- 2.
- 3.
Along with code released at github.com/jiasenlu/ViLBERT_beta.
- 4.
Publicly available on visualdialog.org/data.
- 5.
References
de Vries, H., Strub, F., Chandar, S., Pietquin, O., Larochelle, H., Courville, A.: GuessWhat?! visual object discovery through multi-modal dialogue. In: CVPR (2017)
Das, A., et al.: Visual dialog. In: CVPR (2017)
Strub, F., De Vries, H., Mary, J., Piot, B., Courville, A., Pietquin, O.: End-to-end optimization of goal-driven and visually grounded dialogue systems, arXiv preprint arXiv:1703.05423 (2017)
Das, A., Kottur, S., Moura, J.M., Lee, S., Batra, D.: Learning cooperative visual dialog agents with deep reinforcement learning. In: ICCV (2017)
Lu, J., Kannan, A., Yang, J., Parikh, D., Batra, D.: Best of both worlds: transferring knowledge from discriminative learning to a generative visual dialog model. In: NIPS (2017)
Massiceti, D., Siddharth, N., Dokania, P.K., Torr, P.H.: FLIPDIAL: a generative model for two-way visual dialogue. In: CVPR (2018)
Wu, Q., Wang, P., Shen, C., Reid, I., van den Hengel, A.: Are you talking to me? reasoned visual dialog generation through adversarial learning. In: CVPR (2018)
Jain, U., Lazebnik, S., Schwing, A.G.: Two can play this game: visual dialog with discriminative question generation and answering. In: CVPR (2018)
Kottur, S., Moura, J.M., Parikh, D., Batra, D., Rohrbach, M.: Visual coreference resolution in visual dialog using neural module networks. In: ECCV (2018)
Lee, S.-W., Gao, T., Yang, S., Yoo, J., Ha, J.-W.: Large-scale answerer in questioner’s mind for visual dialog question generation. In: ICLR (2019)
Niu, Y., Zhang, H., Zhang, M., Zhang, J., Lu, Z., Wen, J.-R.: Recursive visual attention in visual dialog. In: CVPR (2019)
Zheng, Z., Wang, W., Qi, S., Zhu, S.-C.: Reasoning visual dialogs with structural and partial observations. In: CVPR (2019)
Schwartz, I., Yu, S., Hazan, T., Schwing, A.G.: Factor graph attention. In: CVPR (2019)
Kang, G.-C., Lim, J., Zhang, B.-T.: Dual attention networks for visual reference resolution in visual dialog. In: EMNLP (2019)
Gan, Z., Cheng, Y., Kholy, A.E., Li, L., Liu, J., Gao, J.: Multi-step reasoning via recurrent dual attention for visual dialog. In: ACL (2019)
Kottur, S., Moura, J.M., Parikh, D., Batra, D., Rohrbach, M.: CLEVR-dialog: a diagnostic dataset for multi-round reasoning in visual dialog. In: NAACL (2019)
Murahari, V., Chattopadhyay, P., Batra, D., Parikh, D., Das, A.: Improving generative visual dialog by answering diverse questions. In: EMNLP (2019)
Shekhar, R., et al.: Beyond task success: a closer look at jointly learning to see, ask, and guesswhat. In: NAACL (2019)
Yang, T., Zha, Z.-J., Zhang, H.: Making history matter: gold-critic sequence training for visual dialog. arXiv preprint arXiv:1902.09326 (2019)
Guo, D., Xu, C., Tao, D.: Image-question-answer synergistic network for visual dialog. In: CVPR (2019)
Qi, J., Niu, Y., Huang, J., Zhang, H.: Two causal principles for improving visual dialog, arXiv preprint arXiv:1911.10496 (2019)
Jiang, X., Yu, J., et al.: DualVD: an adaptive dual encoding model for deep visual understanding in visual dialogue. In: AAAI (2020)
Alamri, H., et al.: Audio visual scene-aware dialog. In: CVPR (2019)
de Vries, H., Shuster, K., Batra, D., Parikh, D., Weston, J., Kiela, D.: Talk the walk: navigating new york city through grounded dialogue, arXiv preprint arXiv:1807.03367 (2018)
Nguyen, K., Daumé III, H.: Help, anna! visual navigation with natural multimodal assistance via retrospective curiosity-encouraging imitation learning. In: EMNLP (2019)
Thomason, J., Murray, M., Cakmak, M., Zettlemoyer, L.: Vision-and-dialog navigation (2019)
Zhu, Y., Kiros, R., et al.: Aligning books and movies: towards story-like visual explanations by watching movies and reading books. In: ICCV (2015)
Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: ACL (2018)
Antol, S., et al.: VQA: visual question answering. In: ICCV (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)
Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)
Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding with unsupervised learning (2018)
Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)
Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)
Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach, arXiv preprint arXiv:1907.11692 (2019)
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations, arXiv preprint arXiv:1909.11942 (2019)
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., Le, Q.L.: XLNET: generalized autoregressive pretraining for language understanding, arXiv preprint arXiv:1906.08237 (2019)
Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer, arXiv preprint arXiv:1910.10683 (2019)
Zhang, Y., et al.: DialoGPT: large-scale generative pre-training for conversational response generation, arXiv preprint arXiv:1911.00536 (2019)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV (2015)
Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. IJCV (2017)
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding, arXiv preprint arXiv:1804.07461 (2018)
Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: NeurIPS (2019)
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)
Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers, arXiv preprint arXiv:1908.07490 (2019)
Chen, Y.-C., et al.: UNITER: Learning UNiversal Image-TExt Representations, arXiv preprint arXiv:1909.11740 (2019)
Li, G., Duan, N., Fang, Y., Jiang, D., Zhou, M.: Unicoder-VL: a universal encoder for vision and language by cross-modal pre-training, arXiv preprint arXiv:1908.06066 (2019)
Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations, arXiv preprint arXiv:1908.08530 (2019)
Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: a joint model for video and language representation learning, arXiv preprint arXiv:1904.01766 (2019)
Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: CVPR (2019)
Suhr, A., Zhou, S., Zhang, A., Zhang, I., Bai, H., Artzi, Y.: A corpus for reasoning about natural language grounded in photographs. In: ACL (2019)
Xie, N., Lai, F., Doran, D., Kadav, A.: Visual entailment: a novel task for fine-grained image understanding, arXiv preprint arXiv:1901.06706 (2019)
Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. In: TACL (2014)
Lee, K.-H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: ECCV (2018)
Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.L.: ReferItGame: referring to objects in photographs of natural scenes. In: EMNLP (2014)
Hao, W., Li, C., Li, X., Carin, L., Gao, J.: Towards learning a generic agent for vision-and-language navigation via pre-training. In: CVPR (2020)
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 8024–8035, Curran Associates Inc. (2019)
Wolf, T., Sanh, V., Chaumond, J., Delangue, C.: TransferTransfo: a transfer learning approach for neural network based conversational agents, arXiv preprint arXiv:1901.08149 (2019)
Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering, arXiv preprint arXiv:1707.07998 (2017)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: ECCV (2014)
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Lewis, M., et al.: Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension, arXiv preprint arXiv:1910.13461 (2019)
Acknowledgments
The Georgia Tech effort was supported in part by NSF, AFRL, DARPA, ONR YIPs, ARO PECASE, Amazon. AD was supported by fellowships from Facebook, Adobe, Snap Inc. 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 the U.S. Government, or any sponsor.
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
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Murahari, V., Batra, D., Parikh, D., Das, A. (2020). Large-Scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12363. Springer, Cham. https://doi.org/10.1007/978-3-030-58523-5_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-58523-5_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58522-8
Online ISBN: 978-3-030-58523-5
eBook Packages: Computer ScienceComputer Science (R0)