@inproceedings{gan2020large-scale,
author = {Gan, Zhe and Chen, Yen-Chun and Li, Linjie and Zhu, Chen and Cheng, Yu and Liu, JJ (Jingjing)},
title = {Large-Scale Adversarial Training for Vision-and-Language Representation Learning},
organization = {ACM},
booktitle = {NeurIPS 2020},
year = {2020},
month = {December},
abstract = {We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning. VILLA consists of two training stages: (i) task-agnostic adversarial pre-training; followed by (ii) task-specific adversarial finetuning. Instead of adding adversarial perturbations on image pixels and textual tokens, we propose to perform adversarial training in the embedding space of each modality. To enable large-scale training, we adopt the “free” adversarial training strategy and combine it with KL-divergence-based regularization to promote higher invariance in the embedding space. We apply VILLA to current best-performing V+L models, and achieve a new state of the art on a wide range of tasks, including Visual Question Answering, Visual Commonsense Reasoning, Image-Text Retrieval, Referring Expression Comprehension, Visual Entailment, and NLVR.},
url = {http://approjects.co.za/?big=en-us/research/publication/large-scale-adversarial-training-for-vision-and-language-representation-learning/},
}