We propose a novel and adaptive feature space distillation method (AFSD) to reduce the communication overhead among distributed computers. The proposed improves Codistillation process by supporting longer update interval rates. AFSD performs knowledge distillates across models infrequently provides flexibility in terms of exploring diverse variations training process. perform sharing instead ou...

Few-shot classification (FSC) targeting at classifying unseen classes with few labelled samples is still a challenging task. Recent works show that transfer-learning based approaches are competitive meta-learning ones, which usually pre-train convolutional neural networks (CNN)-based network using cross-entropy (CE) loss and throw away the last layer to post-process novel classes. Hereby, they ...

It would be a natural expectation that only major peaks, not all of them, make an important contribution to the characterization XRD pattern. We developed scheme can identify which peaks are relavant what extent by using auto-encoder technique construct feature space for peak patterns. Individual patterns projected onto single point in two-dimensional constructed method. If is significantly shi...

Targets and objects registration and tracking in a sequence of images play an important role in various areas. One of the methods in image registration is feature-based algorithm which is accomplished in two steps. The first step includes finding features of sensed and reference images. In this step, a scale space is used to reduce the sensitivity of detected features to the scale changes. Afterw...