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

Authors: Zhiwei Zhang, Shifeng Chen, Lei Sun

IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The experimental results on CIFAR-10, MNIST, and FMNIST 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. In this section, the proposed P-KDGAN is evaluated on the well-known CIFAR-10 [Krizhevsky, 2009], MNIST [Le Cun and Cortes, 2005] and FMNIST [Xiao et al., 2017] datasets.
Researcher Affiliation Academia Zhiwei Zhang1,2 , Shifeng Chen1 and Lei Sun2 1Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China 2School of Information and Electronics, Beijing Institute of Technology, China
Pseudocode Yes Algorithm 1 Progressive Knowledge Distillation with GANs
Open Source Code No The paper does not contain any explicit statement about releasing the source code or provide a link to a code repository.
Open Datasets Yes In this section, the proposed P-KDGAN is evaluated on the well-known CIFAR-10 [Krizhevsky, 2009], MNIST [Le Cun and Cortes, 2005] and FMNIST [Xiao et al., 2017] datasets.
Dataset Splits Yes For the three experimental datasets, the training and testing partitions remain as default. every experiment on the CIFAR-10 dataset is trained with 5000 samples and tested with 10,000 samples.
Hardware Specification Yes All the reported results are implemented using the Py Torch framework [Paszke et al., 2017] on NVIDIA TITAN 2080Ti.
Software Dependencies No The paper mentions 'Py Torch framework' but does not specify a version number for PyTorch or any other software dependencies.
Experiment Setup Yes In the experiments, the batch size and epoch are set to 1 and 500 respectively. Adam [Kingma and Ba, 2015] is used for training with a learning rate of 0.002. The intermediate layers in the teacher networks are set to 64-128-256 channels following the OCGAN [Perera et al., 2019]. The student networks in each dataset utilize intermediate representations with 8-16-64 channels, 2-4-8 channels and 1-2-4 channels respectively.