Qilong Wang

Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification

2022 · arXiv (Cornell University)

Few-shot classification is a challenging problem as only very few training examples are given for each new task. One of the effective research lines to address this challenge focuses on learning deep representations driven by …

Joint loss function design in diffractive optical neural network classifiers for high power efficiency

2025 · Optics Express

The high speed, wide bandwidth, and parallel processing capabilities of a diffractive optical neural network (DONN) stimulate its applications in computer vision for image recognition and information processing tasks. This paper presents a joint loss …