European Conference on Computer Vision (ECCV)
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.
Donglai Xiang, Timur Bagautdinov, Tuur Stuyck, Fabian Prada, Javier Romero, Weipeng Xu, Shunsuke Saito, Jingfan Guo, Breannan Smith, Takaaki Shiratori, Yaser Sheikh, Jessica Hodgins, Chenglei Wu
Ludwig Sidenmark, Mark Parent, Chi-Hao Wu, Joannes Chan, Michael Glueck, Daniel Wigdor, Tovi Grossman, Marcello Giordano
Xingyi Zhou, Rohit Girdhar, Armand Joulin, Philipp Krähenbühl, Ishan Misra
