Interactive Image Segmentation with Cross-Modality Vision Transformers

TL;DR

This paper introduces a cross-modality vision transformer for interactive image segmentation that leverages mutual information between modalities, achieving superior performance and stability over previous models.

Contribution

It proposes a novel cross-modality transformer architecture that effectively models relations between different data modalities for interactive segmentation.

Findings

Outperforms previous state-of-the-art models on several benchmarks.

Demonstrates high stability and reduced failure cases.

Shows potential as a practical annotation tool.

Abstract

Interactive image segmentation aims to segment the target from the background with the manual guidance, which takes as input multimodal data such as images, clicks, scribbles, and bounding boxes. Recently, vision transformers have achieved a great success in several downstream visual tasks, and a few efforts have been made to bring this powerful architecture to interactive segmentation task. However, the previous works neglect the relations between two modalities and directly mock the way of processing purely visual information with self-attentions. In this paper, we propose a simple yet effective network for click-based interactive segmentation with cross-modality vision transformers. Cross-modality transformers exploits mutual information to better guide the learning process. The experiments on several benchmarks show that the proposed method achieves superior performance in comparison to the previous state-of-the-art models. The stability of our method in term of avoiding failure cases shows its potential to be a practical annotation tool. The code and pretrained models will be released under https://github.com/lik1996/iCMFormer.