Decompose and Attribute: Boosting Generalizable Open-Set Object Detection via Objectness Score
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (15) · 12286-12294
DOI: 10.1609/aaai.v40i15.38220 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yuxuan Yuan und 6 weiteren Autor:innen.
Abstract (Originalsprache)
Open-set object detection (OSOD) aims to recognize known object categories while localizing previously unseen instances. However, real-world scenarios often involve co-occurring domain shifts and novel object categories. Existing OSOD methods typically overlook domain shifts, relying on source-trained representations that entangle domain-specific style with semantic content, thereby hindering generalization to both unseen domains and novel categories. To address this challenge, we propose a unified framework, termed DecOmpose and ATtribute (DOAT), which disentangles domain-specific style from semantic structure, thereby facilitating generalizable object detection. DOAT employs wavelet-based feature decomposition to separate style information from high-frequency structural details, thus enabling an explicit separation of domain and category shifts. To account for domain shift, the low-frequency components are perturbed within a style subspace to simulate diverse domain appearances. For unknown object discovery, the high-frequency components are utilized to estimate objectness scores via an attribution mechanism that fuses wavelet energy with semantic distance to known-category prototypes. Extensive experiments on standard open-set benchmarks have demonstrated the superior generalization performance of DOAT.
Zitieren
APA
Yuan, Y., Wei, L., Tang, L., Chen, C., Cai, Z., Huang, Y., & Ding, X. (2026). Decompose and Attribute: Boosting Generalizable Open-Set Object Detection via Objectness Score. Proceedings of the AAAI Conference on Artificial Intelligence, 40(15), 12286-12294. https://doi.org/10.1609/aaai.v40i15.38220
Vancouver
Yuan Y, Wei L, Tang L, Chen C, Cai Z, Huang Y, et al. Decompose and Attribute: Boosting Generalizable Open-Set Object Detection via Objectness Score. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(15):12286-12294. doi:10.1609/aaai.v40i15.38220
BibTeX
@article{Yuan2026,
author = {Yuan, Yuxuan and Wei, Lichen and Tang, Luyao and Chen, Chaoqi and Cai, Zheyuan and Huang, Yue and Ding, Xinghao},
title = {Decompose and Attribute: Boosting Generalizable Open-Set Object Detection via Objectness Score},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {15},
pages = {12286--12294},
doi = {10.1609/aaai.v40i15.38220}
}
EUVIMED