EUVIMEDEUVIMED entdecken
Crossref

Learning Time in Static Classifiers

Xi Ding, Lei Wang, Piotr Koniusz, Yongsheng Gao

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (25) · 20816-20825

DOI: 10.1609/aaai.v40i25.39221 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xi Ding und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-world visual data rarely presents as isolated, static instances. Instead, it often evolves gradually over time through variations in pose, lighting, object state, or scene context. However, conventional classifiers are typically trained under the assumption of temporal independence, limiting their ability to capture such dynamics. We propose a simple yet effective framework that equips standard feedforward classifiers with temporal reasoning, all without modifying model architectures or introducing recurrent modules. At the heart of our approach is a novel Support-Exemplar-Query (SEQ) learning paradigm, which structures training data into temporally coherent trajectories. These trajectories enable the model to learn class-specific temporal prototypes and align prediction sequences via a differentiable soft-DTW loss. A multi-term objective further promotes semantic consistency and temporal smoothness. By interpreting input sequences as evolving feature trajectories, our method introduces a strong temporal inductive bias through loss design alone. This proves highly effective in both static and temporal tasks: it enhances performance on fine-grained and ultra-fine-grained image classification, and delivers precise, temporally consistent predictions in video anomaly detection. Despite its simplicity, our approach bridges static and temporal learning in a modular and data-efficient manner, requiring only a simple classifier on top of pre-extracted features.

Zitieren

APA

Ding, X., Wang, L., Koniusz, P., & Gao, Y. (2026). Learning Time in Static Classifiers. Proceedings of the AAAI Conference on Artificial Intelligence, 40(25), 20816-20825. https://doi.org/10.1609/aaai.v40i25.39221

Vancouver

Ding X, Wang L, Koniusz P, Gao Y. Learning Time in Static Classifiers. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(25):20816-20825. doi:10.1609/aaai.v40i25.39221

BibTeX
@article{Ding2026,
  author = {Ding, Xi and Wang, Lei and Koniusz, Piotr and Gao, Yongsheng},
  title = {Learning Time in Static Classifiers},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {25},
  pages = {20816--20825},
  doi = {10.1609/aaai.v40i25.39221}
}
Kostenlos starten →