Saved in:
Bibliographic Details
Main Authors: Yang, Xuzheng, Liu, Junzhuo, Wang, Peng, Wang, Guoqing, Yang, Yang, Shen, Heng Tao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.20104
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913891415490560
author Yang, Xuzheng
Liu, Junzhuo
Wang, Peng
Wang, Guoqing
Yang, Yang
Shen, Heng Tao
author_facet Yang, Xuzheng
Liu, Junzhuo
Wang, Peng
Wang, Guoqing
Yang, Yang
Shen, Heng Tao
contents Referring Expression Comprehension (REC) is a foundational cross-modal task that evaluates the interplay of language understanding, image comprehension, and language-to-image grounding. It serves as an essential testing ground for Multimodal Large Language Models (MLLMs). To advance this field, we introduced a new REC dataset in our previous conference paper, characterized by two key features. First, it is designed with controllable difficulty levels, requiring multi-level fine-grained reasoning across object categories, attributes, and multi-hop relationships. Second, it incorporates negative text and images generated through fine-grained editing and augmentation, explicitly testing a model's ability to reject scenarios where the target object is absent, an often overlooked yet critical challenge in existing datasets. In this extended work, we propose two new methods to tackle the challenges of fine-grained REC by combining the strengths of Specialist Models and MLLMs. The first method adaptively assigns simple cases to faster, lightweight models and reserves complex ones for powerful MLLMs, balancing accuracy and efficiency. The second method lets a specialist generate a set of possible object regions, and the MLLM selects the most plausible one using its reasoning ability. These collaborative strategies lead to significant improvements on our dataset and other challenging benchmarks. Our results show that combining specialized and general-purpose models offers a practical path toward solving complex real-world vision-language tasks. Our dataset and code are available at https://github.com/sleepyshep/FineCops-Ref.
format Preprint
id arxiv_https___arxiv_org_abs_2502_20104
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration
Yang, Xuzheng
Liu, Junzhuo
Wang, Peng
Wang, Guoqing
Yang, Yang
Shen, Heng Tao
Computer Vision and Pattern Recognition
Referring Expression Comprehension (REC) is a foundational cross-modal task that evaluates the interplay of language understanding, image comprehension, and language-to-image grounding. It serves as an essential testing ground for Multimodal Large Language Models (MLLMs). To advance this field, we introduced a new REC dataset in our previous conference paper, characterized by two key features. First, it is designed with controllable difficulty levels, requiring multi-level fine-grained reasoning across object categories, attributes, and multi-hop relationships. Second, it incorporates negative text and images generated through fine-grained editing and augmentation, explicitly testing a model's ability to reject scenarios where the target object is absent, an often overlooked yet critical challenge in existing datasets. In this extended work, we propose two new methods to tackle the challenges of fine-grained REC by combining the strengths of Specialist Models and MLLMs. The first method adaptively assigns simple cases to faster, lightweight models and reserves complex ones for powerful MLLMs, balancing accuracy and efficiency. The second method lets a specialist generate a set of possible object regions, and the MLLM selects the most plausible one using its reasoning ability. These collaborative strategies lead to significant improvements on our dataset and other challenging benchmarks. Our results show that combining specialized and general-purpose models offers a practical path toward solving complex real-world vision-language tasks. Our dataset and code are available at https://github.com/sleepyshep/FineCops-Ref.
title New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.20104