SegLLM: Multi-round Reasoning Segmentation

TL;DR

SegLLM is a multi-round reasoning segmentation model that uses conversational memory and multimodal reasoning to improve interactive segmentation tasks, outperforming existing methods and enhancing single-round segmentation performance.

Contribution

Introduces SegLLM, a novel multi-round interactive segmentation model leveraging conversational memory and multimodal reasoning, with superior performance on the MRSeg benchmark.

Findings

SegLLM outperforms existing methods by over 20% on MRSeg.

Training on multi-round data improves single-round segmentation by 5.5% cIoU.

SegLLM enables chat-like reasoning for complex segmentation tasks.

Abstract

We present SegLLM, a novel multi-round interactive reasoning segmentation model that enhances LLM-based segmentation by exploiting conversational memory of both visual and textual outputs. By leveraging a mask-aware multimodal LLM, SegLLM re-integrates previous segmentation results into its input stream, enabling it to reason about complex user intentions and segment objects in relation to previously identified entities, including positional, interactional, and hierarchical relationships, across multiple interactions. This capability allows SegLLM to respond to visual and text queries in a chat-like manner. Evaluated on the newly curated MRSeg benchmark, SegLLM outperforms existing methods in multi-round interactive reasoning segmentation by over 20%. Additionally, we observed that training on multi-round reasoning segmentation data enhances performance on standard single-round referring segmentation and localization tasks, resulting in a 5.5% increase in cIoU for referring expression segmentation and a 4.5% improvement in Acc@0.5 for referring expression localization.