P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection

Zhang, Zhiwei; Chen, Shifeng; Sun, Lei

doi:10.24963/ijcai.2020/448

Cited by 20 publications

(11 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhiwei Zhnag and Lei Sun [7] proposed an algorithm which uses the concept of along Progressive Knowledge Distillation with Generative Adversarial Networks (GANs), where two different GAN models were combined using the distillation loss. They compared this novel approach with OC-SVM (One Class-Support Vector Machine), Kernel Density Estimation (KDE) and Variational Autoencoder (VAE).…”

Section: Literature Surveymentioning

confidence: 99%

LPRNet: A Novel Approach for Novelty Detection in Networking Packets

Chauhan¹,

Agarwal²,

Jothi³

et al. 2022

IJACSA

View full text Add to dashboard Cite

Novelty Detection is a task of recognition of abnormal data points within a given system. Recently, this task has been performed using Deep Learning Autoencoders, but they face several drawbacks which include the problem of identity mapping, adversarial perturbations and optimization algorithms. In this paper, we have proposed a novel approach LPRNet, a Denoising Autoencoder which uses algorithms such as Least Trimmed Square, Projected Gradient Descent and Robust Principal Component Analysis, to solve the above-mentioned problems. LRPNet is then trained and tested on NSL-KDD dataset, and experiments have been performed using Accuracy as performance metric for comparing the existing models with the proposed model. The results show that LRPNet has the maximum accuracy of 95.9% and performed better than all the previous state-of-the-art algorithms.

show abstract

Section: Literature Surveymentioning

confidence: 99%

LPRNet: A Novel Approach for Novelty Detection in Networking Packets

Chauhan¹,

Agarwal²,

Jothi³

et al. 2022

IJACSA

View full text Add to dashboard Cite

show abstract

“…Progressive Knowledge Distillation (P-KDGAN) Progressive knowledge distillation (P-KDGAN) [105] proposes one-class method designed to distill knowledge from teacher network and transfer it to a student network through a distillation loss. For this purpose, P-KDGAN trains two GAN networks on given one-class training data, namely student and teacher networks.…”

Section: Inter Class Splitting (Ics)mentioning

confidence: 99%

One-Class Classification: A Survey

Perera,

Oza,

Patel

2021

Preprint

View full text Add to dashboard Cite

One-Class Classification (OCC) is a special case of multi-class classification, where data observed during training is from a single positive class. The goal of OCC is to learn a representation and/or a classifier that enables recognition of positively labeled queries during inference. This topic has received considerable amount of interest in the computer vision, machine learning and biometrics communities in recent years. In this article, we provide a survey of classical statistical and recent deep learning-based OCC methods for visual recognition. We discuss the merits and drawbacks of existing OCC approaches and identify promising avenues for research in this field. In addition, we present a discussion of commonly used datasets and evaluation metrics for OCC.

show abstract

“….00 96. AnoGAN [42], ALOCC [40], ADGAN [11], OCGAN [33], GANomaly [2], P-KDGAN [55] and DGEO [17]. For the semi-supervised anomaly detection approaches, we consider SSAD [19], SS-DGM [20] and Deep SAD [39].…”

Section: Experiments On Natural Imagesmentioning

confidence: 99%

“…The main challenge in anomaly detection is that anomalous samples are diverse and inexhaustible. To bypass the unfeasible task of collect-ing a representative set of anomalous samples, many approaches [40,33,55] resort to unsupervised learning so that only normal samples are needed for model training.…”

Section: Introductionmentioning

confidence: 99%

ESAD: End-to-end Deep Semi-supervised Anomaly Detection

Huang

Zhang

et al. 2020

Preprint

View full text Add to dashboard Cite

This paper explores semi-supervised anomaly detection, a more practical setting for anomaly detection where a small set of labeled outlier samples are provided in addition to a large amount of unlabeled data for training. Rethinking the optimization target of anomaly detection, we propose a new objective function that measures the KLdivergence between normal and anomalous data, and prove that two factors: the mutual information between the data and latent representations, and the entropy of latent representations, constitute an integral objective function for anomaly detection. To resolve the contradiction in simultaneously optimizing the two factors, we propose a novel encoder-decoder-encoder structure, with the first encoder focusing on optimizing the mutual information and the second encoder focusing on optimizing the entropy. The two encoders are enforced to share similar encoding with a consistent constraint on their latent representations. Extensive experiments have revealed that the proposed method significantly outperforms several state-of-the-arts on multiple benchmark datasets, including medical diagnosis and several classic anomaly detection benchmarks. Source code will be made publicly available.

show abstract

P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection

Cited by 20 publications

References 35 publications

LPRNet: A Novel Approach for Novelty Detection in Networking Packets

LPRNet: A Novel Approach for Novelty Detection in Networking Packets

One-Class Classification: A Survey

ESAD: End-to-end Deep Semi-supervised Anomaly Detection

Contact Info

Product

Resources

About