MetaMax: Improved Open-Set Deep Neural Networks via Weibull Calibration
This work addresses the problem of identifying novel classes at inference time for deep neural networks, representing an incremental improvement over existing methods.
The paper tackles open-set recognition by introducing MetaMax, a post-processing technique that improves upon OpenMax by directly modeling class activation vectors, eliminating the need for computing class mean activation vectors and distances. Experimental results show that MetaMax outperforms OpenMax and is comparable to other state-of-the-art approaches.
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.