Cross-Modal Self-Attention Network for Referring Image Segmentation

TL;DR

This paper introduces a cross-modal self-attention network that effectively captures long-range dependencies between language and visual features for referring image segmentation, improving performance over previous methods.

Contribution

The paper proposes a novel cross-modal self-attention module and a gated multi-level fusion module to better model long-range dependencies and integrate multi-level features in referring image segmentation.

Findings

Outperforms state-of-the-art methods on four datasets

Effectively captures long-range correlations between language and image

Adaptive focus on important words and regions

Abstract

We consider the problem of referring image segmentation. Given an input image and a natural language expression, the goal is to segment the object referred by the language expression in the image. Existing works in this area treat the language expression and the input image separately in their representations. They do not sufficiently capture long-range correlations between these two modalities. In this paper, we propose a cross-modal self-attention (CMSA) module that effectively captures the long-range dependencies between linguistic and visual features. Our model can adaptively focus on informative words in the referring expression and important regions in the input image. In addition, we propose a gated multi-level fusion module to selectively integrate self-attentive cross-modal features corresponding to different levels in the image. This module controls the information flow of features at different levels. We validate the proposed approach on four evaluation datasets. Our proposed approach consistently outperforms existing state-of-the-art methods.