Few-Shot Open-Set Recognition Using Meta-Learning
By Bo Liu, Hao Kang, Haoxiang Li, Gang Hua, Nuno Vasconcelos. 2020
129 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Computational Mechanics, Meta & Continual Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Serge J. Belongie
- Vladlen Koltun
- Quoc V. Le
- Trevor Darrell
- Kilian Q. Weinberger
- Sergey Levine
- Luc Van Gool
- Boyi Li
In Computational Mechanics
- René Ranftl
- Vladlen Koltun
- Serge J. Belongie
- Kilian Q. Weinberger
- Philip H. S. Torr
- Iasonas Kokkinos
- Jitendra Malik
- Alan L. Yuille
In Meta & Continual Learning
Citations in the corpus
- Language-driven Semantic Segmentation (2022, background): “Few-shot approaches (Shaban et al., 2017; Rakelly et al., 2018; Siam et al., 2019; Wang et al., 2019; Zhang et al., 2019; Nguyen & Todorovic, 2019; Liu et al., 2020b; Wang et al., 2020; Tian et al., 2020; Boudiaf et al., 2021; Min et al., 2021) offer ways to learn to segment novel classes based on…”
- Generalized Out-of-Distribution Detection: A Survey (2021, unknown): “methods also leveraged contrastive learning to learn more compact clusters for known classes [199], [200], which enlarge the distance between ID and OOD.”
- Visual Product Search Benchmark (2026, unknown): “…approaches focus on modeling similarity relationships and have been shown to generalize more effectively in open-set scenarios where new classes are introduced at test time, whereas traditional softmax-based classifiers tend to overfit to training classes and perform poorly on novel instances [20].”