Skip to content
AI News HubLIVE
Original source2 min read

Partition, Refine, and Detect: Preserving Novel Category Capacity in Open-Vocabulary Object Detection

Summary

The paper proposes PR-OVD, a partition-and-refine framework that explicitly reserves capacity for novel categories and strengthens category separation, achieving an average 6.5% proportional improvement on novel categories over state-of-the-art methods and integrating seamlessly into different detector architectures.

SourcearXiv Computer VisionAuthor: Wei Zhang, Zhu Teng, Zhixiang Chi, Junnan Zou, Yi Liu, Jianping Fan
Partition, Refine, and Detect: Preserving Novel Category Capacity in Open-Vocabulary Object Detection
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 8 Nov 2026]

Title:Partition, Refine, and Detect: Preserving Novel Category Capacity in Open-Vocabulary Object Detection

View a PDF of the paper titled Partition, Refine, and Detect: Preserving Novel Category Capacity in Open-Vocabulary Object Detection, by Wei Zhang and 5 other authors

View PDF HTML (experimental)

Abstract:Open-vocabulary object detection (OVD) expects the model trained on base classes to recognize both base and novel classes at inference. Typical methods rely on CLIP-style vision-language embeddings, yet the learned space is often biased toward base categories, with limited effective capacity preserved for novel concepts. Such a base-dominated representation can compress novel semantics, leading to semantic collapse and mis-calibrated confidence at inference. To address this issue, we present PR-OVD, a partition-and-refine framework that explicitly reserves capacity for novel categories and strengthens category separation, while being seamlessly integrated into different detector architectures. Specifically, PR-OVD first performs coarse partitioning to build global divisions for base, novel, and an explicit background partition in both visual and textual modalities, preventing object-irrelevant embeddings from leaking into category-specific representations. It then applies category-level refinement within each partition to sharpen decision boundaries and alleviate the lack of fine-grained region-level pretraining in CLIP. To further provide reliable visual anchors for novel categories, we design a cognitively inspired Structure Prompt (SP) that encodes both egocentric attributes and allocentric context, facilitating stable partition-and-refine learning. Extensive experiments on two OVD benchmarks show that PR-OVD delivers an average 6.5\% proportional improvement on novel categories over the state-of-the-art methods. Notably, PR-OVD also benefits other open-vocabulary tasks, including segmentation and classification, further confirming its effectiveness and generality.

Comments: IEEE Transactions on Multimedia (TMM)

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

Cite as: arXiv:2611.12976 [cs.CV]

(or arXiv:2611.12976v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.12976

arXiv-issued DOI via DataCite

Submission history

From: Zhixiang Chi [view email] [v1] Sun, 8 Nov 2026 04:13:25 UTC (3,618 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Partition, Refine, and Detect: Preserving Novel Category Capacity in Open-Vocabulary Object Detection, by Wei Zhang and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs cs.LG

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • PR-OVD performs coarse partitioning to create global divisions for base, novel, and background in both visual and textual modalities.
  • Category-level refinement within each partition sharpens decision boundaries and alleviates CLIP's lack of fine-grained region-level pretraining.
  • A cognitively inspired Structure Prompt (SP) encodes egocentric attributes and allocentric context to provide reliable visual anchors for novel categories.
  • Experiments on two OVD benchmarks show an average 6.5% proportional improvement on novel categories, with benefits extending to segmentation and classification.

Highlights and analysis are generated automatically and may contain errors. Check the original source.