TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformer

TL;DR

TransVG++ introduces a fully Transformer-based framework for visual grounding that simplifies multi-modal fusion, improves training efficiency, and achieves state-of-the-art results across multiple datasets.

Contribution

It proposes TransVG++, a novel end-to-end Transformer-based model that replaces complex fusion modules with a unified architecture leveraging Vision Transformer and language-conditioned fusion.

Findings

Achieves state-of-the-art performance on five datasets.

Simplifies the fusion process with a unified Transformer architecture.

Demonstrates improved training efficiency and robustness.

Abstract

In this work, we explore neat yet effective Transformer-based frameworks for visual grounding. The previous methods generally address the core problem of visual grounding, i.e., multi-modal fusion and reasoning, with manually-designed mechanisms. Such heuristic designs are not only complicated but also make models easily overfit specific data distributions. To avoid this, we first propose TransVG, which establishes multi-modal correspondences by Transformers and localizes referred regions by directly regressing box coordinates. We empirically show that complicated fusion modules can be replaced by a simple stack of Transformer encoder layers with higher performance. However, the core fusion Transformer in TransVG is stand-alone against uni-modal encoders, and thus should be trained from scratch on limited visual grounding data, which makes it hard to be optimized and leads to sub-optimal performance. To this end, we further introduce TransVG++ to make two-fold improvements. For one thing, we upgrade our framework to a purely Transformer-based one by leveraging Vision Transformer (ViT) for vision feature encoding. For another, we devise Language Conditioned Vision Transformer that removes external fusion modules and reuses the uni-modal ViT for vision-language fusion at the intermediate layers. We conduct extensive experiments on five prevalent datasets, and report a series of state-of-the-art records.