Distribution Networks for Open Set Learning

TL;DR

This paper introduces distribution networks for open set learning, enabling models to detect and differentiate novel classes by modeling their probability distributions in a learned latent space.

Contribution

It proposes a novel approach that models different novel classes using probability distributions and updates these models for improved classification in open set scenarios.

Findings

Accurately detects novel classes in image datasets

Effectively models novel classes for subsequent classification

Improves open set learning performance on MNIST and CIFAR10

Abstract

In open set learning, a model must be able to generalize to novel classes when it encounters a sample that does not belong to any of the classes it has seen before. Open set learning poses a realistic learning scenario that is receiving growing attention. Existing studies on open set learning mainly focused on detecting novel classes, but few studies tried to model them for differentiating novel classes. In this paper, we recognize that novel classes should be different from each other, and propose distribution networks for open set learning that can model different novel classes based on probability distributions. We hypothesize that, through a certain mapping, samples from different classes with the same classification criterion should follow different probability distributions from the same distribution family. A deep neural network is learned to map the samples in the original feature space to a latent space where the distributions of known classes can be jointly learned with the network. We additionally propose a distribution parameter transfer and updating strategy for novel class modeling when a novel class is detected in the latent space. By novel class modeling, the detected novel classes can serve as known classes to the subsequent classification. Our experimental results on image datasets MNIST and CIFAR10 show that the distribution networks can detect novel classes accurately, and model them well for the subsequent classification tasks.