Few-Shot Open-Set Recognition using Meta-Learning
arXiv:2005.13713
Abstract
The problem of open-set recognition is considered. While previous approaches only consider this problem in the context of large-scale classifier training, we seek a unified solution for this and the low-shot classification setting. It is argued that the classic softmax classifier is a poor solution for open-set recognition, since it tends to overfit on the training classes. Randomization is then proposed as a solution to this problem. This suggests the use of meta-learning techniques, commonly used for few-shot classification, for the solution of open-set recognition. A new oPen sEt mEta LEaRning (PEELER) algorithm is then introduced. This combines the random selection of a set of novel classes per episode, a loss that maximizes the posterior entropy for examples of those classes, and a new metric learning formulation based on the Mahalanobis distance. Experimental results show that PEELER achieves state of the art open set recognition performance for both few-shot and large-scale recognition. On CIFAR and miniImageNet, it achieves substantial gains in seen/unseen class detection AUROC for a given seen-class classification accuracy.
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- Matching Networks for One Shot Learning
- Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
- Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
- A Two-Stage Approach to Few-Shot Learning for Image Recognition
- Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
- Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
- Large-Scale Long-Tailed Recognition in an Open World
- Generative OpenMax for Multi-Class Open Set Classification
- Open-Set Recognition Using Intra-Class Splitting