Seg-ReSearch: Segmentation with Interleaved Reasoning and External Search

TL;DR

Seg-ReSearch introduces a segmentation approach that combines reasoning with external search to handle dynamic, real-world queries beyond the fixed knowledge of large language models, improving performance on challenging benchmarks.

Contribution

It proposes a novel segmentation paradigm with interleaved reasoning and external search, overcoming the knowledge limitations of existing models.

Findings

Significant performance improvements on OK-VOS and other benchmarks.

Effective hierarchical reward design for training reasoning capabilities.

Demonstrated ability to handle open-world, domain-specific, and up-to-date information.

Abstract

Segmentation based on language has been a popular topic in computer vision. While recent advances in multimodal large language models (MLLMs) have endowed segmentation systems with reasoning capabilities, these efforts remain confined by the frozen internal knowledge of MLLMs, which limits their potential for real-world scenarios that involve up-to-date information or domain-specific concepts. In this work, we propose \textbf{Seg-ReSearch}, a novel segmentation paradigm that overcomes the knowledge bottleneck of existing approaches. By enabling interleaved reasoning and external search, Seg-ReSearch empowers segmentation systems to handle dynamic, open-world queries that extend beyond the frozen knowledge of MLLMs. To effectively train this capability, we introduce a hierarchical reward design that harmonizes initial guidance with progressive incentives, mitigating the dilemma between sparse outcome signals and rigid step-wise supervision. For evaluation, we construct OK-VOS, a challenging benchmark that explicitly requires outside knowledge for video object segmentation. Experiments on OK-VOS and two existing reasoning segmentation benchmarks demonstrate that our Seg-ReSearch improves state-of-the-art approaches by a substantial margin. Code and data will be released at https://github.com/iSEE-Laboratory/Seg-ReSearch.