3 papers
cs.LG2025
Unveiling the Training Dynamics of ReLU Networks through a Linear Lens
Longqing Ye
Deep neural networks, particularly those employing Rectified Linear Units (ReLU), are often perceived as complex, high-dimensional, non-linear systems. This complexity poses a sign…
cs.CV2025
iMedImage Technical Report
Ran Wei, ZhiXiong Lan, Qing Yan +3
Background: Chromosome karyotype analysis is crucial for diagnosing hereditary diseases, yet detecting structural abnormalities remains challenging. While AI has shown promise in m…
cs.CV2021
Dynamic Clone Transformer for Efficient Convolutional Neural Netwoks
Longqing Ye
Convolutional networks (ConvNets) have shown impressive capability to solve various vision tasks. Nevertheless, the trade-off between performance and efficiency is still a challeng…