ADMM-SRNet: Alternating Direction Method of Multipliers Based Sparse Representation Network for One-Class Classification.

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.

[Developing the core competencies of long-term care professionals].

Longer average life expectancies and an ageing society have made long-term care an urgent and important issue in Taiwan. Although the implementation of Long-Term Care Ten-year Project four years ago has begun showing success in terms of assessing Taiwan's needs in terms of long-term care services and resources, there has been little forward progress in terms of training, recruiting and maintaining more competent professionals in the long-term care sector. This paper explores the current state of long-term care competency in Taiwan and educational strategies in place to improve the competency of long-term care professionals. Results indicate that the term geriatric competency embraces sub-competencies in direct care, communication, assessment, teamwork, cultural sensitivities and career care competencies. The term long-term care competency embraces the sub-competencies of supervision, management, information technology, resource management, and organizational skill. As a main contributor to effective long-term care, the nursing profession must employ effective strategies to develop competency-based education. Also, the profession must have an adequate supply of competent manpower to effectively respond to Taiwan's aging society.