DeepStreamOS: Spot the Unknown!

Convolutional Neural Networks (CNNs) have proven to be highly effective in achieving state-of-the-art results for visual recognition problems. However, their performance is limited when the train and test data distributions differ, and when new classes emerge. This is a significant issue in real-world scenarios where data evolves, and existing classes change. Traditional neural networks can only label instances with classes they have been trained on, and cannot identify unknown classes. This limitation can have serious consequences in safety-critical systems.