VinVL: Revisiting Visual Representations in Vision-Language Models
arXiv:2101.00529
Abstract
This paper presents a detailed study of improving visual representations for vision language (VL) tasks and develops an improved object detection model to provide object-centric representations of images. Compared to the most widely used \emph{bottom-up and top-down} model \cite{anderson2018bottom}, the new model is bigger, better-designed for VL tasks, and pre-trained on much larger training corpora that combine multiple public annotated object detection datasets. Therefore, it can generate representations of a richer collection of visual objects and concepts. While previous VL research focuses mainly on improving the vision-language fusion model and leaves the object detection model improvement untouched, we show that visual features matter significantly in VL models. In our experiments we feed the visual features generated by the new object detection model into a Transformer-based VL fusion model \oscar \cite{li2020oscar}, and utilize an improved approach \short\ to pre-train the VL model and fine-tune it on a wide range of downstream VL tasks. Our results show that the new visual features significantly improve the performance across all VL tasks, creating new state-of-the-art results on seven public benchmarks. We will release the new object detection model to public.
References in corpus (5)
- VisualBERT: A Simple and Performant Baseline for Vision and Language
- The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
- Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers
- Large-Scale Adversarial Training for Vision-and-Language Representation Learning
- ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph
Cited by in corpus (4)
- Florence: A New Foundation Model for Computer Vision
- Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
- STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training
- Winning the ICCV'2021 VALUE Challenge: Task-aware Ensemble and Transfer Learning with Visual Concepts