Advancing Visual Large Language Model for Multi-granular Versatile Perception

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xiang, Wentao, Tan, Haoxian, Wei, Cong, Zhong, Yujie, Li, Dengjie, Yang, Yujiu
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909698713714688
author Xiang, Wentao
Tan, Haoxian
Wei, Cong
Zhong, Yujie
Li, Dengjie
Yang, Yujiu
author_facet Xiang, Wentao
Tan, Haoxian
Wei, Cong
Zhong, Yujie
Li, Dengjie
Yang, Yujiu
contents Perception is a fundamental task in the field of computer vision, encompassing a diverse set of subtasks that can be systematically categorized into four distinct groups based on two dimensions: prediction type and instruction type. Notably, existing researches often focus solely on a limited subset of these potential combinations, which constrains their applicability and versatility across various contexts. In response to this challenge, we present MVP-LM, a Multi-granular and Versatile Perception framework incorporating Visual Large Language Model. Our framework is designed to integrate both word-based and sentence-based perception tasks alongside box and mask predictions within a single architecture. MVP-LM features an innovative multi-granularity decoder in conjunction with a CoT-inspired dataset unification strategy, enabling seamless supervised fine-tuning across a wide spectrum of tasks, including but not limited to panoptic segmentation, detection, grounding, and referring expression segmentation. Furthermore, we introduce a query enhancement strategy aimed at harnessing the decoding and generative capabilities inherent in VLLMs. Extensive experiments conducted across a range of benchmarks in both word-based and sentence-based perception tasks substantiate the efficacy of our framework. The code will be available at https://github.com/xiangwentao666/MVP-LM.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16213
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Advancing Visual Large Language Model for Multi-granular Versatile Perception
Xiang, Wentao
Tan, Haoxian
Wei, Cong
Zhong, Yujie
Li, Dengjie
Yang, Yujiu
Computer Vision and Pattern Recognition
Artificial Intelligence
Perception is a fundamental task in the field of computer vision, encompassing a diverse set of subtasks that can be systematically categorized into four distinct groups based on two dimensions: prediction type and instruction type. Notably, existing researches often focus solely on a limited subset of these potential combinations, which constrains their applicability and versatility across various contexts. In response to this challenge, we present MVP-LM, a Multi-granular and Versatile Perception framework incorporating Visual Large Language Model. Our framework is designed to integrate both word-based and sentence-based perception tasks alongside box and mask predictions within a single architecture. MVP-LM features an innovative multi-granularity decoder in conjunction with a CoT-inspired dataset unification strategy, enabling seamless supervised fine-tuning across a wide spectrum of tasks, including but not limited to panoptic segmentation, detection, grounding, and referring expression segmentation. Furthermore, we introduce a query enhancement strategy aimed at harnessing the decoding and generative capabilities inherent in VLLMs. Extensive experiments conducted across a range of benchmarks in both word-based and sentence-based perception tasks substantiate the efficacy of our framework. The code will be available at https://github.com/xiangwentao666/MVP-LM.
title Advancing Visual Large Language Model for Multi-granular Versatile Perception
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.16213