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

TL;DR

The paper presents the COCONut-PanCap dataset, which enhances panoptic segmentation and grounded captioning with detailed, scene-level annotations to improve vision-language models and image understanding.

Contribution

Introduction of the COCONut-PanCap dataset with fine-grained, region-level captions grounded in panoptic masks, advancing scene understanding and captioning quality.

Findings

Significantly improves model performance on joint segmentation and captioning tasks.

Provides high-quality, densely annotated scene descriptions for better training.

Sets new benchmarks for grounded panoptic segmentation and captioning evaluation.

Abstract

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.