Built independently by an author, for readers. Read the story and support ChapterPal

keyword

subpart segmentation

Subpart segmentation is a fine-grained computer vision task that involves identifying and partitioning the individual sub-components within the larger parts of an object. While standard object segmentation delineates whole entities and part segmentation divides those entities into primary components such as limbs or torso, subpart segmentation operates at a deeper level of hierarchical granularity to isolate finer elements, such as individual fingers on a hand or headlights on a car. By establishing multi-level part-whole relationships, this technique enables visual models to achieve detailed structural comprehension and resolve semantic ambiguities across varying levels of abstraction in complex scenes.

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