DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy

Referring Image Segmentation (RIS) is a challenging task that aims to segment objects in an image based on natural language expressions. While prior studies have predominantly concentrated on improving vision-language interactions and achieving fine-grained localization, a systematic analysis of the fundamental bottlenecks in existing RIS frameworks remains underexplored. To bridge this gap, we propose DeRIS, a novel framework that decomposes RIS into two key components: perception and cognition. This modular decomposition facilitates a systematic analysis of the primary bottlenecks impeding RIS performance. Our findings reveal that the predominant limitation lies not in perceptual deficiencies, but in the insufficient multi-modal cognitive capacity of current models. To mitigate this, we propose a Loopback Synergy mechanism, which enhances the synergy between the perception and cognition modules, thereby enabling precise segmentation while simultaneously improving robust image-text comprehension. Additionally, we analyze and introduce a simple non-referent sample conversion data augmentation to address the long-tail distribution issue related to target existence judgement in general scenarios. Notably, DeRIS demonstrates inherent adaptability to both non- and multi-referents scenarios without requiring specialized architectural modifications, enhancing its general applicability. The codes and models are available atthis https URL.

@article{dai2025_2507.01738,
  title={ DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy },
  author={ Ming Dai and Wenxuan Cheng and Jiang-jiang Liu and Sen Yang and Wenxiao Cai and Yanpeng Sun and Wankou Yang },
  journal={arXiv preprint arXiv:2507.01738},
  year={ 2025 }
}