SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.00764 · NeurIPS · 2023

Hierarchical Open-vocabulary Universal Image Segmentation

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

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
berkeley-hipie/hipie canonical 2 of 4
FunctionStatusWhere it lives
get_images_color_similarity Ran berkeley-hipie/hipie/projects/HIPIE/hipie/hipie_img.py
code served (permissive licence) · get_code("3a4a70eddd103b6f")
unfold_wo_center Ran berkeley-hipie/hipie/projects/HIPIE/hipie/hipie_img.py
code served (permissive licence) · get_code("6bc62d34967e2917")
convert_grounding_to_od_logits Not yet run berkeley-hipie/hipie/projects/HIPIE/hipie/hipie_img.py
code served (permissive licence) · get_code("133372f6b12b6ba0")
vote Not yet run berkeley-hipie/hipie/projects/HIPIE/hipie/demo_lib/demo_utils.py
code served (permissive licence) · get_code("0d78867cbc2d1619")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2307.00764")
get_code_for_paper("2307.00764")
have("2307.00764")

Connect an agent — have() is free.