SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.06963 · IJCAI · 2020

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

Lei Sun, Shifeng Chen, Zhiwei Zhang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.

Abstract

One-class novelty detection is to identify anomalous instances that do not conform to the expected normal instances. In this paper, the Generative Adversarial Networks (GANs) based on encoderdecoder-encoder pipeline are used for detection and achieve state-of-the-art performance. However, deep neural networks are too over-parameterized to deploy on resource-limited devices. Therefore, Progressive Knowledge Distillation with GANs (P-KDGAN) is proposed to learn compact and fast novelty detection networks. The P-KDGAN is a novel attempt to connect two standard GANs by the designed distillation loss for transferring knowledge from the teacher to the student. The progressive learning of knowledge distillation is a twostep approach that continuously improves the performance of the student GAN and achieves better performance than single step methods. In the first step, the student GAN learns the basic knowledge totally from the teacher via guiding of the pretrained teacher GAN with fixed weights. In the second step, joint fine-training is adopted for the knowledgeable teacher and student GANs to further improve the performance and stability. The experimental results on CIFAR-10, MNIST, and FM-NIST show that our method improves the performance of the student GAN by 2.44%, 1.77%, and 1.73% when compressing the computation at ratios of 24.45:1, 311.11:1, and 700:1, respectively.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2007.06963")
get_code_for_paper("2007.06963")
have("2007.06963")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2007.06963.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2007.06963.svg)](https://syntology.ai/paper/2007.06963)

Connect an agent — have() is free.