Much of vision-and-language research focuses on a small but diverse set of independent tasks and supporting datasets often studied in isolation; however, the visually-grounded language understanding skills required for success at these tasks overlap significantly. In this work, we investigate these relationships between vision-and-language tasks by developing a large-scale, multi-task training regime. Our approach culminates in a single model on 12 datasets from four broad categories of task including visual question answering, caption-based image retrieval, grounding referring expressions, and multi-modal verification. Compared to independently trained single-task models, this represents a reduction from approximately 3 billion parameters to 270 million while simultaneously improving performance by 2.05 points on average across tasks. We use our multi-task framework to perform in-depth analysis of the effect of joint training diverse tasks. Further, we show that finetuning task-specific models from our single multi-task model can lead to further improvements, achieving performance at or above the state-of-the-art.
@article{arxiv.1912.02315,
title = {12-in-1: Multi-Task Vision and Language Representation Learning},
author = {Jiasen Lu and Vedanuj Goswami and Marcus Rohrbach and Devi Parikh and Stefan Lee},
journal= {arXiv preprint arXiv:1912.02315},
year = {2020}
}
Comments
Jiasen Lu and Vedanuj Goswami contributed equally to this work