Deep Learning
a815fe7cad6af20a6c118f2072a881d2-Supplemental-Conference.pdf
Here we collect some frequently asked questions from reviewers and other literature researchers.
On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models
While the performance of DDGMs is impressive, not all of their aspects are fully understood.
A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks
In distributed training of deep neural networks, people usually run Stochastic Gradient Descent (SGD) or its variants on each machine and communicate with other machines periodically.
Unsupervised Representation Transfer for Small Networks: I Believe I Can Distill On-the-Fly
Notably, our ResNet-18, trained with ResNet-50 teacher, achieves 68.3% ImageNet Top-1 accuracy on frozen feature linear evaluation, which is only 1.5% below the
Supplementary Material: Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training
This supplementary material discusses the details of implementation including hyperparameters, network configuration, and the framework protocol in Sec. A. It details the data-centralized and other distributed learning strategies used for
Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training
However, it is not clear how to find the optimal split without sacrificing the overall network performance.