# New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration

arXiv: https://arxiv.org/abs/2502.20104 · HTML: https://mlsanity.com/paper/2502.20104/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 71 of its 79 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## Builds on (most cited first, 30 of 71)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [Ferret: Refer and Ground Anything Anywhere at Any Granularity](https://mlsanity.com/paper/2310.07704/) (2023)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2403.16999/) (2024)
- [TransVG: End-to-End Visual Grounding with Transformers](https://mlsanity.com/paper/2104.08541/) (2021)
- [Modeling Context Between Objects for Referring Expression Understanding](https://mlsanity.com/paper/1608.00525/) (2016)
- [SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality](https://mlsanity.com/paper/2306.14610/) (2023)
- [Universal Instance Perception as Object Discovery and Retrieval](https://mlsanity.com/paper/2303.06674/) (2023)
- [CREPE: Can Vision-Language Foundation Models Reason Compositionally?](https://mlsanity.com/paper/2212.07796/) (2022)
- [A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting](https://mlsanity.com/paper/2312.03594/) (2023)

## Built on by (most cited first, 7 of 7)

- [CVBench: Benchmarking Cross-Video Synergies for Complex Multimodal Reasoning](https://mlsanity.com/paper/2508.19542/) (2025)
- [MedGround: Bridging the Evidence Gap in Medical Vision-Language Models with Verified Grounding Data](https://mlsanity.com/paper/2601.06847/) (2026)
- [Adaptive Global and Fine-Grained Perceptual Fusion for MLLM Embeddings Compatible with Hard Negative Amplification](https://mlsanity.com/paper/2602.05729/) (2026)
- [Multi-label Instance-level Generalised Visual Grounding in Agriculture](https://mlsanity.com/paper/2603.06699/) (2026)
- [Enhancing Medical Visual Grounding via Knowledge-guided Spatial Prompts](https://mlsanity.com/paper/2604.01915/) (2026)
- [GeoRef: Referring Expressions in Geometry via Task Formulation, Synthetic Supervision, and Reinforced MLLM-based Solutions](https://mlsanity.com/paper/2509.21050/) (2025)
- [Towards Open-World Referring Expression Comprehension: A Benchmark with Training-free Multi-task Consistency Checker](https://mlsanity.com/paper/2605.25706/) (2026)

## Abstract (arXiv)

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.