Search Results for author:
Found 5 papers, 0 papers with code
ClaRe: Practical Class Incremental Learning By Remembering Previous Class Representations
Learning new knowledge in the absence of data instances from previous classes or even imbalance samples of both old and new classes makes CIL an ongoing challenging problem.
Image/Video Deep Anomaly Detection: A Survey
AD strongly correlates with the important computer vision and image processing tasks such as image/video anomaly, irregularity and sudden event detection.
G2D: Generate to Detect Anomaly
Previous researches solve this problem as a One-Class Classification (OCC) task where they train a reference model on all of the available samples.
AutoIDS: Auto-encoder Based Method for Intrusion Detection System
These detectors are two encoder-decoder neural networks that are forced to provide a compressed and a sparse representation from the normal flows.
End-to-End Adversarial Learning for Intrusion Detection in Computer Networks
Inspired by the successes of Generative Adversarial Networks (GANs) for training deep models in semi-unsupervised setting, we have proposed an end-to-end deep architecture for IDS.
