MMF: A Loss Extension for Feature Learning in Open Set Recognition

The objective of open set recognition (OSR) is to classify the known classes as well as the unknown classes when the collected samples cannot exhaust all the classes. This paper proposes a loss extension that emphasizes features with larger and smaller magnitudes to find representations that can more effectively separate the known from the unknown classes. Our contributions include: First, we introduce an extension that can be incorporated into different loss functions to find more discriminative representations. Second, we show that the proposed extension can significantly improve the performances of two different types of loss functions on datasets from two different domains. Third, we show that with the proposed extension, one loss function outperforms the others in training time and model accuracy.