Learning multiple gaussian prototypes for open-set recognition

A study on open set recognition methods

“…Inductive methods consider the testing data to be unavailable at the training stage. Most of the existing OSR methods are inductive methods, which can be further divided into three categories according to the difference of their mainly used models: 1) discriminative models which learn decision rules directly , 2) generative models which learn the distributions of the training data [56][57][58][59][60][61][62][63][64][65][66][67][68][69][70][71][72], and 3) causal models which introduce causalities into the statistical models which are lazily learned by DNNs [73][74][75].…”

“…2) Generative Models: With the development of generative models, more and more OSR methods pay attention to adopt generative learning techniques for boosting the model discriminability. Generative OSR models [56][57][58][59][60][61][62][63][64][65][66][67][68][69][70][71][72] mainly learn the distributions from known-class samples, based on which the discrimination criterion of how to both identify unknown-class samples and classify known-class samples is built. According to the specific generative models utilized, these methods can be further divided into three groups: Generative Adversarial Network (GAN)-based methods [64][65][66][67][69][70][71], Auto-Encoder (AE)-based methods [56,57,59,60,62,63,72], and others [58,61,68].…”

“…Similarly, Cao et al [56] also modeled the feature distribution of each known class as a Gaussian Mixture, but they directly modified the Gaussian Mixture VAE [89] rather than embedding the neural Gaussian Mixture Model. Liu et al [57] combined conditional VAE [90] and prototype learning to constrain the feature distribution of each known class as multiple Gaussians, which could also be regarded as a Gaussian Mixture. Considering that some complex feature distribution could not be represent by Single Gaussian or Gaussian Mixture (e.g., sub-Gaussian and super-Gaussian), Sun et al [63] introduced the mixture of exponential power distribution into the network based on a new re-parameterization strategy, which modeled feature distributions from different known classes by discrepant mixtures of exponential power distributions.…”