MTRAG: Multi-Target Referring and Grounding via Hybrid Semantic-Spatial Integration
Yili Ren, Jinyang Du, Xi Liu, Qianxiao Su, Yue Cheng Deng, Hongjue Li
Research Institute of Petroleum Exploration and Development China National Petroleum Corporation (China) Beihang University
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
Fine-grained visual referring and grounding are critical for enhancing scene understanding and enabling various real-world vision-language applications. Although recent studies have extended multimodal large language models (MLLMs) to these tasks, they still face significant challenges in fine-grained multi-target scenarios. To address this, we propose MTRAG, a pixel-level multi-target referring and grounding framework that leverages semantic-spatial collaboration. Specifically, we introduce a Channel Extension Mechanism (CEM) that enables a global image encoder to extract global semantics and multi-region representations while retaining background context, without extra region feature extractors. Moreover, we introduce a grounding branch for pixel-level grounding and design a Hybrid Adapter (HA) to fuse semantic features from the MLLM branch with spatial information from the grounding branch, thereby enhancing the semantic-spatial alignment. For training, we meticulously curate MTRAG-D, a dataset comprising single- and multi-target referring and grounding samples derived from existing datasets and newly synthesized free-form multi-target referring instruction-following data. We also present MTR-Bench, a benchmark for systematic evaluation of multi-target referring. Extensive experiments across five core tasks, including single- and multi-target referring and grounding as well as image-level captioning, show that MTRAG consistently outperforms strong baselines on both multi- and single-target tasks, while maintaining competitive image-level understanding. The code is available at https://github.com/deng-ai-lab/MTRAG.
逐年被引趋势
暂无年度引用数据
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AIMultimodal Machine Learning Applications
Visual Attention and Saliency Detection · Advanced Neural Network Applications