SegLLM: Multi-round Reasoning Segmentation
This addresses the challenge of interactive object segmentation in AI vision systems, offering a novel approach for applications requiring multi-round reasoning, though it builds incrementally on LLM-based segmentation methods.
The paper tackles the problem of multi-round interactive reasoning segmentation by introducing SegLLM, which leverages conversational memory to reason about complex user intentions and relationships across interactions. The model outperforms existing methods by over 20% on the MRSeg benchmark and improves performance on standard single-round tasks by 5.5% in cIoU and 4.5% in Acc@0.5.
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.