Distribution Networks for Open Set Learning

09/20/2018
by   Chengsheng Mao, et al.
0

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. We recognize that novel classes should be different from each other, and propose distribution networks for open set learning that can learn and model different novel classes. 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. We estimate the probability distribution for each known class and a novel class is detected when a sample is not likely to belong to any of the known distributions. Due to the large feature dimension in the original feature space, the probability distributions in the original feature space are difficult to estimate. Distribution networks 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. In the latent space, we also propose a distribution parameter transfer strategy for novel class detection and modeling. 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 and text dataset Ohsumed show that the distribution networks can detect novel classes accurately and model them well for the subsequent classification tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/01/2021

Adversarial Reciprocal Points Learning for Open Set Recognition

Open set recognition (OSR), aiming to simultaneously classify the seen c...
research
09/27/2018

Adaptive Image Stream Classification via Convolutional Neural Network with Intrinsic Similarity Metrics

When performing data classification over a stream of continuously occurr...
research
11/07/2022

Interpreting deep learning output for out-of-distribution detection

Commonly used AI networks are very self-confident in their predictions, ...
research
03/18/2020

OpenGAN: Open Set Generative Adversarial Networks

Many existing conditional Generative Adversarial Networks (cGANs) are li...
research
09/06/2021

Zero-Shot Open Set Detection by Extending CLIP

In a regular open set detection problem, samples of known classes (also ...
research
10/30/2019

Are Out-of-Distribution Detection Methods Effective on Large-Scale Datasets?

Supervised classification methods often assume the train and test data d...
research
11/28/2017

Learning from Between-class Examples for Deep Sound Recognition

Deep learning methods have achieved high performance in sound recognitio...

Please sign up or login with your details

Forgot password? Click here to reset