BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization

TL;DR

BUS introduces a bottom-up patch summarization method for vision-language pre-training, combining bottom-level patch selection and top-level abstraction to improve training efficiency and maintain high task performance.

Contribution

The paper proposes a novel Bottom-Up Patch Summarization approach that balances training efficiency and effectiveness in vision-language models by integrating patch selection and abstraction.

Findings

Boosts training efficiency by 50%

Achieves state-of-the-art results on multiple downstream tasks

Maintains or improves performance with higher input resolutions

Abstract

Vision Transformer (ViT) based Vision-Language Pre-training (VLP) models have demonstrated impressive performance in various tasks. However, the lengthy visual token sequences fed into ViT can lead to training inefficiency and ineffectiveness. Existing efforts address the challenge by either bottom-level patch extraction in the ViT backbone or top-level patch abstraction outside, not balancing training efficiency and effectiveness well. Inspired by text summarization in natural language processing, we propose a Bottom-Up Patch Summarization approach named BUS, coordinating bottom-level extraction and top-level abstraction to learn a concise summary of lengthy visual token sequences efficiently. Specifically, We incorporate a Text-Semantics-Aware Patch Selector (TSPS) into the ViT backbone to perform a coarse-grained visual token extraction and then attach a flexible Transformer-based Patch Abstraction Decoder (PAD) upon the backbone for top-level visual abstraction. This bottom-up collaboration enables our BUS to yield high training efficiency while maintaining or even improving effectiveness. We evaluate our approach on various visual-language understanding and generation tasks and show competitive downstream task performance while boosting the training efficiency by 50\%. Additionally, our model achieves state-of-the-art performance on many downstream tasks by increasing input image resolution without increasing computational costs over baselines.