Detecting Novelties with Empty Classes

S. Uhlemeyer, J. Lienen, E. Hüllermeier, H. Gottschalk, ArXiv:2305.00983 (2023).

Preprint | English
Uhlemeyer, Svenja; Lienen, JulianLibreCat; Hüllermeier, EykeLibreCat; Gottschalk, Hanno
For open world applications, deep neural networks (DNNs) need to be aware of previously unseen data and adaptable to evolving environments. Furthermore, it is desirable to detect and learn novel classes which are not included in the DNNs underlying set of semantic classes in an unsupervised fashion. The method proposed in this article builds upon anomaly detection to retrieve out-of-distribution (OoD) data as candidates for new classes. We thereafter extend the DNN by $k$ empty classes and fine-tune it on the OoD data samples. To this end, we introduce two loss functions, which 1) entice the DNN to assign OoD samples to the empty classes and 2) to minimize the inner-class feature distances between them. Thus, instead of ground truth which contains labels for the different novel classes, the DNN obtains a single OoD label together with a distance matrix, which is computed in advance. We perform several experiments for image classification and semantic segmentation, which demonstrate that a DNN can extend its own semantic space by multiple classes without having access to ground truth.
Publishing Year
Journal Title

Cite this

Uhlemeyer S, Lienen J, Hüllermeier E, Gottschalk H. Detecting Novelties with Empty Classes. arXiv:230500983. Published online 2023.
Uhlemeyer, S., Lienen, J., Hüllermeier, E., & Gottschalk, H. (2023). Detecting Novelties with Empty Classes. In arXiv:2305.00983.
@article{Uhlemeyer_Lienen_Hüllermeier_Gottschalk_2023, title={Detecting Novelties with Empty Classes}, journal={arXiv:2305.00983}, author={Uhlemeyer, Svenja and Lienen, Julian and Hüllermeier, Eyke and Gottschalk, Hanno}, year={2023} }
Uhlemeyer, Svenja, Julian Lienen, Eyke Hüllermeier, and Hanno Gottschalk. “Detecting Novelties with Empty Classes.” ArXiv:2305.00983, 2023.
S. Uhlemeyer, J. Lienen, E. Hüllermeier, and H. Gottschalk, “Detecting Novelties with Empty Classes,” arXiv:2305.00983. 2023.
Uhlemeyer, Svenja, et al. “Detecting Novelties with Empty Classes.” ArXiv:2305.00983, 2023.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
Restricted Closed Access


Marked Publications

Open Data LibreCat


arXiv 2305.00983

Search this title in

Google Scholar