3 papers
cs.LG2021
Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples
Yi Xiang Marcus Tan, Penny Chong, Jiamei Sun +3
Few-shot classifiers have been shown to exhibit promising results in use cases where user-provided labels are scarce. These models are able to learn to predict novel classes simply…
cs.CR2020
Detection of Adversarial Supports in Few-shot Classifiers Using Self-Similarity and Filtering
Yi Xiang Marcus Tan, Penny Chong, Jiamei Sun +3
Few-shot classifiers excel under limited training samples, making them useful in applications with sparsely user-provided labels. Their unique relative prediction setup offers oppo…
cs.LG2020
Simple and Effective Prevention of Mode Collapse in Deep One-Class Classification
Penny Chong, Lukas Ruff, Marius Kloft +1
Anomaly detection algorithms find extensive use in various fields. This area of research has recently made great advances thanks to deep learning. A recent method, the deep Support…