计算机科学
自然语言处理
常识推理
判决
人工智能
变压器
答疑
利用
代表(政治)
政治学
计算机安全
量子力学
政治
物理
电压
法学
作者
Weijie Su,Xizhou Zhu,Yue Cao,Bin Li,Lewei Lu,Furu Wei,Jifeng Dai
出处
期刊:International Conference on Learning Representations
日期:2020-04-30
被引量:214
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI