X
Xin Wei
Researcher at Chinese Academy of Sciences
Publications - 5
Citations - 32
Xin Wei is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Deep learning & MNIST database. The author has an hindex of 1, co-authored 3 publications receiving 10 citations.
Papers
More filters
Journal ArticleDOI
Space Debris Detection Using Feature Learning of Candidate Regions in Optical Image Sequences
TL;DR: The proposed feature learning of candidate regions (FLCR) method has good performance when estimating and removing background, and it can detect low SNR space debris with high detection probability.
Journal ArticleDOI
Parallel Multistage Wide Neural Network
TL;DR: A parallel multistage wide neural network composed of multiple stages to classify different parts of data that can work well on both image and nonimage data and have very competitive accuracy compared to learning models.
Journal ArticleDOI
Scalable Wide Neural Network: A Parallel, Incremental Learning Model Using Splitting Iterative Least Squares
TL;DR: In this article, the authors proposed a scalable wide neural network (SWNN), composed of multiple multi-channel wide RBF neural networks (MWRBF), which focuses on different regions of data and nonlinear transformations can be performed with Gaussian kernels.
Journal ArticleDOI
Prototype-Based Self-Adaptive Distribution Calibration for Few-Shot Image Classification
TL;DR: Li et al. as discussed by the authors proposed a prototype-based self-adaptive distribution calibration framework for estimating ground-truth distribution accurately and selfadaptive hyperparameter optimization for different application scenarios.
Journal ArticleDOI
An Efficient Multi-Objective Evolutionary Zero-Shot Neural Architecture Search Framework for Image Classification
TL;DR: Zhang et al. as mentioned in this paper proposed an efficient multi-objective evolutionary zero-shot NAS framework by evaluating architectures with zero-cost metrics, which can be calculated with randomly initialized models in a training-free manner.