Evidential Prior Guided Neural Collapse for Open World Object Detection
IEEE Transactions on Circuits and Systems for Video Technology · 2026-08 · 36 (8) · 12140-12155
DOI: 10.1109/tcsvt.2026.3682583 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-08. Verfasst von Kewen Xia und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science and Technology Commission of Shanghai Municipality.
Abstract (Originalsprache)
Open World Object Detection (OWOD) faces a fundamental dilemma: maintaining a stable representation for known classes while reserving flexible space for discovering unknown objects. Existing methods, while improving recall, often fail to assign discriminative confidence scores to unknown instances, resulting in critically low Average Precision (U-AP) and representation degradation during incremental learning. To remedy this, we propose the Evidential Prior Guided Neural Collapse (ENC) framework. ENC unifies representation learning and uncertainty quantification via a Geometric-Evidence Coupling mechanism. Unlike previous approaches, we map evidential support directly to the angular alignment with Simplex Equiangular Tight Frame (ETF) prototypes. Theoretically, the evidential prior functions as a geometric regularizer: it maximizes equiangular separation for confident known samples, while constraining ambiguous queries to approximate an isotropic uniform distribution via distributional regularization. Furthermore, to mitigate decision conflicts in self-supervised learning, we propose a dissonance-aware objectness optimization strategy that mines informative samples near the decision boundary. Extensive experiments on M-OWODB and S-OWODB benchmarks demonstrate that ENC sets a new state-of-the-art. Notably, it achieves a significant improvement in unknown class discovery, boosting U-AP from $\approx 1\%$ to 9.2%, while exhibiting superior robustness against catastrophic forgetting in challenging incremental scenarios.
Förderung
- National Natural Science Foundation of China
- Science and Technology Commission of Shanghai Municipality
Zitieren
APA
Xia, K., Yue, X., Liu, W., Wei, Z., Zhu, J., Yang, A., & Peng, Y. (2026). Evidential Prior Guided Neural Collapse for Open World Object Detection. IEEE Transactions on Circuits and Systems for Video Technology, 36(8), 12140-12155. https://doi.org/10.1109/tcsvt.2026.3682583
Vancouver
Xia K, Yue X, Liu W, Wei Z, Zhu J, Yang A, et al. Evidential Prior Guided Neural Collapse for Open World Object Detection. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(8):12140-12155. doi:10.1109/tcsvt.2026.3682583
BibTeX
@article{Xia2026,
author = {Xia, Kewen and Yue, Xiaodong and Liu, Wei and Wei, Zhipeng and Zhu, Jianxiang and Yang, Ao and Peng, Yaxin},
title = {Evidential Prior Guided Neural Collapse for Open World Object Detection},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {8},
pages = {12140--12155},
doi = {10.1109/tcsvt.2026.3682583}
}
EUVIMED