VL-BERT: Pre-training of Generic Visual-Linguistic Representations
Published in
International Conference on Learning Representa...(2019)External Links:
TL
TL;DR
A new pre-trainable generic representation for visual-linguistic tasks, called Visual-Linguistic BERT (VL-BERT), which adopts the simple yet powerful Transformer model as the backbone, and extends it to take both visual and linguistic embedded features as input.
Abstract
We introduce a new pre-trainable generic representation for visual-linguistic tasks, called Visual-Linguistic BERT (VL-BERT for short). VL-BERT adopts the simple yet powerful Transformer model as the backbone, and extends it to take both visual and linguistic embedded features as input. In it, each element of the input is either of a word from the input sentence, or a region-of-interest (RoI) from the input image. It is designed to fit for most of the visual-linguistic downstream tasks. To better exploit the generic representation, we pre-train VL-BERT on the massive-scale Conceptual Captions dataset, together with text-only corpus. Extensive empirical analysis demonstrates that the pre-training procedure can better align the visual-linguistic clues and benefit the downstream tasks, such as visual commonsense reasoning, visual question answering and referring expression comprehension. It is worth noting that VL-BERT achieved the first place of single model on the leaderboard of the VCR benchmark. Code is released at \url{this https URL}.
References52 items
1
5分で分かる!? 有名論文ナナメ読み：Jacob Devlin et al. : BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding
2
Learning Video Representations using Contrastive Bidirectional Transformer
3
LXMERT: Learning Cross-Modality Encoder Representations from Transformers
4
Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training
5