Vision-Language Intelligence: Tasks, Representation Learning, and Large Models

TL;DR

This survey reviews the evolution of vision-language intelligence, highlighting task-specific methods, pre-training techniques, and large-scale models that leverage raw image-text data for improved multimodal understanding.

Contribution

It provides a comprehensive chronological overview of vision-language research, emphasizing recent advances in large-scale models and data utilization for better generalization.

Findings

Progression from task-specific to large-scale models

Effective use of raw image-text data for zero-shot learning

Emerging trends in modality cooperation and unified representations

Abstract

This paper presents a comprehensive survey of vision-language (VL) intelligence from the perspective of time. This survey is inspired by the remarkable progress in both computer vision and natural language processing, and recent trends shifting from single modality processing to multiple modality comprehension. We summarize the development in this field into three time periods, namely task-specific methods, vision-language pre-training (VLP) methods, and larger models empowered by large-scale weakly-labeled data. We first take some common VL tasks as examples to introduce the development of task-specific methods. Then we focus on VLP methods and comprehensively review key components of the model structures and training methods. After that, we show how recent work utilizes large-scale raw image-text data to learn language-aligned visual representations that generalize better on zero or few shot learning tasks. Finally, we discuss some potential future trends towards modality cooperation, unified representation, and knowledge incorporation. We believe that this review will be of help for researchers and practitioners of AI and ML, especially those interested in computer vision and natural language processing.