SplitGround: Long-Chain Reasoning Split via Modular Multi-Expert Collaboration for Training-Free Scene Knowledge-Guided Visual Grounding
Big Data and Cognitive Computing · 14.08.2025 · 9 (8) · 209
DOI: 10.3390/bdcc9080209 ↗Kurz gefasst
Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 14.08.2025. Verfasst von Xilong Qin und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Hunan Provincial Natural Science Foundation of China, China Association for Science and Technology.
Abstract (Originalsprache)
Scene Knowledge-guided Visual Grounding (SK-VG) is a multi-modal detection task built upon conventional visual grounding (VG) for human–computer interaction scenarios. It utilizes an additional passage of scene knowledge apart from the image and context-dependent textual query for referred object localization. Due to the inherent difficulty in directly establishing correlations between the given query and the image without leveraging scene knowledge, this task imposes significant demands on a multi-step knowledge reasoning process to achieve accurate grounding. Off-the-shelf VG models underperform under such a setting due to the requirement of detailed description in the query and a lack of knowledge inference based on implicit narratives of the visual scene. Recent Vision–Language Models (VLMs) exhibit improved cross-modal reasoning capabilities. However, their monolithic architectures, particularly in lightweight implementations, struggle to maintain coherent reasoning chains across sequential logical deductions, leading to error accumulation in knowledge integration and object localization. To address the above-mentioned challenges, we propose SplitGround—a collaborative framework that strategically decomposes complex reasoning processes by fusing the input query and image with knowledge through two auxiliary modules. Specifically, it implements an Agentic Annotation Workflow (AAW) for explicit image annotation and a Synonymous Conversion Mechanism (SCM) for semantic query transformation. This hierarchical decomposition enables VLMs to focus on essential reasoning steps while offloading auxiliary cognitive tasks to specialized modules, effectively splitting long reasoning chains into manageable subtasks with reduced complexity. Comprehensive evaluations on the SK-VG benchmark demonstrate the significant advancements of our method. Remarkably, SplitGround attains an accuracy improvement of 15.71% on the hard split of the test set over the previous training-required SOTA, using only a compact VLM backbone without fine-tuning, which provides new insights for knowledge-intensive visual grounding tasks.
Förderung
- National Natural Science Foundation of China
- Hunan Provincial Natural Science Foundation of China
- China Association for Science and Technology
Zitieren
APA
Qin, X., Hu, Y., Wu, W., Li, X., & Yin, Q. (2025). SplitGround: Long-Chain Reasoning Split via Modular Multi-Expert Collaboration for Training-Free Scene Knowledge-Guided Visual Grounding. Big Data and Cognitive Computing, 9(8), 209. https://doi.org/10.3390/bdcc9080209
Vancouver
Qin X, Hu Y, Wu W, Li X, Yin Q. SplitGround: Long-Chain Reasoning Split via Modular Multi-Expert Collaboration for Training-Free Scene Knowledge-Guided Visual Grounding. Big Data and Cognitive Computing. 2025;9(8):209. doi:10.3390/bdcc9080209
BibTeX
@article{Qin2025,
author = {Qin, Xilong and Hu, Yue and Wu, Wansen and Li, Xinmeng and Yin, Quanjun},
title = {SplitGround: Long-Chain Reasoning Split via Modular Multi-Expert Collaboration for Training-Free Scene Knowledge-Guided Visual Grounding},
journal = {Big Data and Cognitive Computing},
year = {2025},
volume = {9},
number = {8},
pages = {209},
doi = {10.3390/bdcc9080209}
}
EUVIMED