TY - JOUR
T1 - ADMM-SRNet
T2 - Alternating Direction Method of Multipliers Based Sparse Representation Network for One-Class Classification
AU - Chiou, Chien Yu
AU - Lee, Kuang Ting
AU - Huang, Chun Rong
AU - Chung, Pau Choo
N1 - Publisher Copyright:
© 1992-2012 IEEE.
PY - 2023
Y1 - 2023
N2 - One-class classification aims to learn one-class models from only in-class training samples. Because of lacking out-of-class samples during training, most conventional deep learning based methods suffer from the feature collapse problem. In contrast, contrastive learning based methods can learn features from only in-class samples but are hard to be end-to-end trained with one-class models. To address the aforementioned problems, we propose alternating direction method of multipliers based sparse representation network (ADMM-SRNet). ADMM-SRNet contains the heterogeneous contrastive feature (HCF) network and the sparse dictionary (SD) network. The HCF network learns in-class heterogeneous contrastive features by using contrastive learning with heterogeneous augmentations. Then, the SD network models the distributions of the in-class training samples by using dictionaries computed based on ADMM. By coupling the HCF network, SD network and the proposed loss functions, our method can effectively learn discriminative features and one-class models of the in-class training samples in an end-to-end trainable manner. Experimental results show that the proposed method outperforms state-of-the-art methods on CIFAR-10, CIFAR-100 and ImageNet-30 datasets under one-class classification settings. Code is available at https://github.com/nchucvml/ADMM-SRNet.
AB - One-class classification aims to learn one-class models from only in-class training samples. Because of lacking out-of-class samples during training, most conventional deep learning based methods suffer from the feature collapse problem. In contrast, contrastive learning based methods can learn features from only in-class samples but are hard to be end-to-end trained with one-class models. To address the aforementioned problems, we propose alternating direction method of multipliers based sparse representation network (ADMM-SRNet). ADMM-SRNet contains the heterogeneous contrastive feature (HCF) network and the sparse dictionary (SD) network. The HCF network learns in-class heterogeneous contrastive features by using contrastive learning with heterogeneous augmentations. Then, the SD network models the distributions of the in-class training samples by using dictionaries computed based on ADMM. By coupling the HCF network, SD network and the proposed loss functions, our method can effectively learn discriminative features and one-class models of the in-class training samples in an end-to-end trainable manner. Experimental results show that the proposed method outperforms state-of-the-art methods on CIFAR-10, CIFAR-100 and ImageNet-30 datasets under one-class classification settings. Code is available at https://github.com/nchucvml/ADMM-SRNet.
UR - http://www.scopus.com/inward/record.url?scp=85159785024&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85159785024&partnerID=8YFLogxK
U2 - 10.1109/TIP.2023.3274488
DO - 10.1109/TIP.2023.3274488
M3 - Article
C2 - 37171924
AN - SCOPUS:85159785024
SN - 1057-7149
VL - 32
SP - 2843
EP - 2856
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
ER -