MetaMax: Improved Open-Set Deep Neural Networks via Weibull Calibration

Zongyao Lyu, Nolan B. Gutierrez, William J. Beksi; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, 2023, pp. 439-443

Abstract


Open-set recognition refers to the problem in which classes that were not seen during training appear at inference time. This requires the ability to identify instances of novel classes while maintaining discriminative capability for closed-set classification. OpenMax was the first deep neural network-based approach to address open-set recognition by calibrating the predictive scores of a standard closed-set classification network. In this paper we present MetaMax, a more effective post-processing technique that improves upon contemporary methods by directly modeling class activation vectors. MetaMax removes the need for computing class mean activation vectors (MAVs) and distances between a query image and a class MAV as required in OpenMax. Experimental results show that MetaMax outperforms OpenMax and is comparable in performance to other state-of-the-art approaches.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lyu_2023_WACV, author = {Lyu, Zongyao and Gutierrez, Nolan B. and Beksi, William J.}, title = {MetaMax: Improved Open-Set Deep Neural Networks via Weibull Calibration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {January}, year = {2023}, pages = {439-443} }