UniT: Multimodal Multitask Learning with a Unified Transformer

作者：Ronghang Hu, Amanpreet Singh · 发表于：2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 年份：2021 · DOI：10.1109/iccv48922.2021.00147 · 被引用次数：282 · 研究领域：Multimodal Machine Learning Applications、Topic Modeling、Domain Adaptation and Few-Shot Learning

We propose UniT, a Unified Transformer model to simultaneously learn the most prominent tasks across different domains, ranging from object detection to natural language understanding and multimodal reasoning. Based on the transformer encoder-decoder architecture, our UniT model encodes each input modality with an encoder and makes predictions on each task with a shared decoder over the encoded input representations, followed by task-specific output heads. The entire model is jointly trained end-to-end with losses from each task. Compared to previous efforts on multi-task learning with transformers, we share the same model parameters across all tasks instead of separately fine-tuning task-specific models and handle a much higher variety of tasks across different domains. In our experiments, we learn 7 tasks jointly over 8 datasets, achieving strong performance on each task with significantly fewer parameters. Our code is available in MMF at https://mmf.sh.