Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Few-Shot Open-Set Recognition using Meta-Learning

About

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.

Bo Liu, Hao Kang, Haoxiang Li, Gang Hua, Nuno Vasconcelos• 2020

Related benchmarks

TaskDatasetResultRank
Domain Adaptive Few-Shot Open-Set RecognitionMiniImageNet to CUB
Accuracy30.71
26
Few-Shot Open-Set RecognitionminiImageNet (test)
Accuracy80.61
22
Domain Adaptive Few-Shot Open-Set RecognitionOffice-Home Real-World to Clipart (test)
Accuracy (%)20.16
22
Domain Adaptive Few-Shot Open-Set RecognitionDomainNet Real to Clipart
Accuracy0.2252
22
Domain Adaptive Few-Shot Open-Set RecognitionDomainNet Real to Painting
Accuracy23.24
22
Domain Adaptive Few-Shot Open-Set RecognitionDomainNet Clipart to Painting
Accuracy24.82
22
Few-Shot Open-Set RecognitiontieredImageNet (test)
Accuracy84.1
20
Few-Shot Open-Set Recognitiontiered-ImageNet 5-shot
AUROC73.27
20
Few-Shot Open-Set Recognitionmini-ImageNet 1-shot
AUROC60.57
20
Few-Shot Open-Set Recognitionmini-ImageNet 5-shot
Accuracy80.61
20
Showing 10 of 12 rows

Other info

Follow for update