Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

part-level segmentation

Part-level segmentation is a computer vision process that divides an object within an image or 3D model into its constituent semantic components or subparts, assigning a distinct mask to each sub-region. While standard semantic and instance segmentation methods identify and delineate entire objects as unified entities, part-level segmentation functions at a finer, hierarchical level of granularity by breaking down those entities into smaller structural elements, such as separating a human figure into a head, torso, and limbs, or a vehicle into wheels, doors, and headlights. This granular decomposition enables visual systems to analyze complex object geometries, internal spatial relationships, and localized features necessary for detailed scene understanding, robotics, and fine-grained visual recognition.

1 item

Hierarchical Open-vocabulary Universal Image Segmentation

Hierarchical Open-vocabulary Universal Image Segmentation

Xudong Wang, Shufan Li, Konstantinos Kallidromitis, Yusuke Kato, Kazuki Kozuka, Trevor Darrell

OrganizationsPanasonicUniversity of California Berkeley

Why you should read this

Presents HIPIE, a unified open-vocabulary framework that resolves segmentation ambiguity across multiple granularities by incorporating hierarchical visual representations alongside decoupled text-image fusion mechanisms for stuff and thing categories.

Open-vocabulary image segmentation aims to partition an image into semantic regions according to arbitrary text descriptions. However, complex visual scenes can be naturally decomposed into simpler parts and abstracted at multiple levels of granularity, introducing inherent segmentation ambiguity. Unlike existing methods that typically sidestep this ambiguity and treat it as an external factor, our approach actively incorporates a hierarchical representation encompassing different semantic-levels into the learning process. We also propose a decoupled text-image fusion mechanism and representation learning modules for both “things” and “stuff”.1 Additionally, we systematically examine the differences that exist in the textual and visual features between these types of categories. Our resulting model, named HIPIE, tackles HIerarchical, oPen-vocabulary, and unIvErsal segmentation tasks within a unified framework. Benchmarked on over 40 datasets, e.g., ADE20K, COCO, Pascal-VOC Part, RefCOCO/RefCOCOg, ODinW and SeginW, HIPIE achieves the state-of-the-art results at various levels of image comprehension, including semantic-level (e.g., semantic segmentation), instance-level (e.g., panoptic/referring segmentation and object detection), as well as part-level (e.g., part/subpart segmentation) tasks.

Added

2026-09-26