ReMamber: Referring Image Segmentation with Mamba Twister
This work addresses efficiency and fusion challenges in multi-modal vision-language tasks, offering an incremental improvement for researchers in computer vision.
The paper tackles the high computational cost of transformers in referring image segmentation by proposing ReMamber, which integrates Mamba for linear complexity and a Mamba Twister block for multi-modal fusion, achieving competitive results on three benchmarks.
Referring Image Segmentation~(RIS) leveraging transformers has achieved great success on the interpretation of complex visual-language tasks. However, the quadratic computation cost makes it resource-consuming in capturing long-range visual-language dependencies. Fortunately, Mamba addresses this with efficient linear complexity in processing. However, directly applying Mamba to multi-modal interactions presents challenges, primarily due to inadequate channel interactions for the effective fusion of multi-modal data. In this paper, we propose ReMamber, a novel RIS architecture that integrates the power of Mamba with a multi-modal Mamba Twister block. The Mamba Twister explicitly models image-text interaction, and fuses textual and visual features through its unique channel and spatial twisting mechanism. We achieve competitive results on three challenging benchmarks with a simple and efficient architecture. Moreover, we conduct thorough analyses of ReMamber and discuss other fusion designs using Mamba. These provide valuable perspectives for future research. The code has been released at: https://github.com/yyh-rain-song/ReMamber.