VD-BERT: A Unified Vision and Dialog Transformer with BERT

Abstract

Visual dialog is a challenging vision-language task, where a dialog agent needs to answer a series of questions through reasoning on the image content and dialog history. Prior work has mostly focused on various attention mechanisms to model such intricate interactions. By contrast, in this work, we propose VD-BERT, a simple yet effective framework of unified vision-dialog Transformer that leverages the pretrained BERT language models for Visual Dialog tasks. The model is unified in that (1) it captures all the interactions between the image and the multi-turn dialog using a single-stream Transformer encoder, and (2) it supports both answer ranking and answer generation seamlessly through the same architecture. More crucially, we adapt BERT for the effective fusion of vision and dialog contents via visually grounded training. Without the need of pretraining on external vision-language data, our model yields new state of the art, achieving the top position in both single-model and ensemble settings (74.54 and 75.35 NDCG scores) on the visual dialog leaderboard. Our code and pretrained models are released at https://github.com/salesforce/VD-BERT.

arXiv commentEMNLP 2020 (14 pages)

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Neural Machine Translation by Jointly Learning to Align and Translate
• Sequence to Sequence Learning with Neural Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
• VisualBERT: A Simple and Performant Baseline for Vision and Language
• VL-BERT: Pre-training of Generic Visual-Linguistic Representations
• Visual Reference Resolution using Attention Memory for Visual Dialog
• Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model

Cited by in corpus (8)

• Large-Scale Adversarial Training for Vision-and-Language Representation Learning
• A Multimodal Memes Classification: A Survey and Open Research Issues
• A Closer Look at the Robustness of Vision-and-Language Pre-trained Models
• OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
• VD-PCR: Improving Visual Dialog with Pronoun Coreference Resolution
• Cross-Media Keyphrase Prediction: A Unified Framework with Multi-Modality Multi-Head Attention and Image Wordings
• Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation
• GoG: Relation-aware Graph-over-Graph Network for Visual Dialog