Open-Set Recognition with Gaussian Mixture Variational Autoencoders
This addresses open-set classification for machine learning systems by improving accuracy and robustness, though it is incremental as it builds on existing variational autoencoder methods.
The paper tackled the problem of open-set recognition by training a Gaussian mixture variational autoencoder to cooperatively learn reconstruction and class-based clustering in the latent space, achieving an average F1 improvement of 29.5% in classification results.
In inference, open-set classification is to either classify a sample into a known class from training or reject it as an unknown class. Existing deep open-set classifiers train explicit closed-set classifiers, in some cases disjointly utilizing reconstruction, which we find dilutes the latent representation's ability to distinguish unknown classes. In contrast, we train our model to cooperatively learn reconstruction and perform class-based clustering in the latent space. With this, our Gaussian mixture variational autoencoder (GMVAE) achieves more accurate and robust open-set classification results, with an average F1 improvement of 29.5%, through extensive experiments aided by analytical results.