COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Deng, Xueqing, Yu, Qihang, Athar, Ali, Yang, Chenglin, Yang, Linjie, Jin, Xiaojie, Shen, Xiaohui, Chen, Liang-Chieh
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910814225563648
author Deng, Xueqing
Yu, Qihang
Athar, Ali
Yang, Chenglin
Yang, Linjie
Jin, Xiaojie
Shen, Xiaohui
Chen, Liang-Chieh
author_facet Deng, Xueqing
Yu, Qihang
Athar, Ali
Yang, Chenglin
Yang, Linjie
Jin, Xiaojie
Shen, Xiaohui
Chen, Liang-Chieh
contents This paper introduces the COCONut-PanCap dataset, created to enhance panoptic segmentation and grounded image captioning. Building upon the COCO dataset with advanced COCONut panoptic masks, this dataset aims to overcome limitations in existing image-text datasets that often lack detailed, scene-comprehensive descriptions. The COCONut-PanCap dataset incorporates fine-grained, region-level captions grounded in panoptic segmentation masks, ensuring consistency and improving the detail of generated captions. Through human-edited, densely annotated descriptions, COCONut-PanCap supports improved training of vision-language models (VLMs) for image understanding and generative models for text-to-image tasks. Experimental results demonstrate that COCONut-PanCap significantly boosts performance across understanding and generation tasks, offering complementary benefits to large-scale datasets. This dataset sets a new benchmark for evaluating models on joint panoptic segmentation and grounded captioning tasks, addressing the need for high-quality, detailed image-text annotations in multi-modal learning.
format Preprint
id arxiv_https___arxiv_org_abs_2502_02589
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation
Deng, Xueqing
Yu, Qihang
Athar, Ali
Yang, Chenglin
Yang, Linjie
Jin, Xiaojie
Shen, Xiaohui
Chen, Liang-Chieh
Computer Vision and Pattern Recognition
This paper introduces the COCONut-PanCap dataset, created to enhance panoptic segmentation and grounded image captioning. Building upon the COCO dataset with advanced COCONut panoptic masks, this dataset aims to overcome limitations in existing image-text datasets that often lack detailed, scene-comprehensive descriptions. The COCONut-PanCap dataset incorporates fine-grained, region-level captions grounded in panoptic segmentation masks, ensuring consistency and improving the detail of generated captions. Through human-edited, densely annotated descriptions, COCONut-PanCap supports improved training of vision-language models (VLMs) for image understanding and generative models for text-to-image tasks. Experimental results demonstrate that COCONut-PanCap significantly boosts performance across understanding and generation tasks, offering complementary benefits to large-scale datasets. This dataset sets a new benchmark for evaluating models on joint panoptic segmentation and grounded captioning tasks, addressing the need for high-quality, detailed image-text annotations in multi-modal learning.
title COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.02589