PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects

Abstract

We present , a part-level foundation model for locating and identifying both objects and parts in images. Through a unified framework, accomplishes detection, segmentation, and grounding of instances at any granularity in the open world scenario. Specifically, we propose a Q-Former to construct the hierarchical relationship between objects and parts, parsing every object into corresponding semantic parts. By incorporating a large amount of object-level data, the hierarchical relationships can be extended, enabling to recognize a rich variety of parts. We conduct comprehensive studies to validate the effectiveness of our method, achieves the state-of-the-art performance across various part-level tasks and obtain competitive results on object-level tasks. The proposed significantly enhances hierarchical modeling capabilities and part-level perception over our previous GLEE model. Further analysis indicates that the hierarchical cognitive ability of is able to facilitate a detailed comprehension in images for mLLMs. The model and code will be released at https://provencestar.github.io/ PartGLEE-Vision/. all_papers.txt decode_tex_noligatures.sh decode_tex_noligatures.sh~ decode_tex.sh decode_tex.sh~ ECCV_abstracts.csv ECCV_abstracts_good.csv ECCV.csv ECCV.csv~ ECCV_new.csv generate_list.sh generate_list.sh~ generate_overview.sh gen.sh gen.sh~ HOWTO HOWTO~ pdflist pdflist.copied RCS snippet.html Equal Technical Contribution. Work done during Junfeng’s internship at ByteDance. to Xiang Bai . † Correspondence