Implicit Gradient Regularization

隐式梯度正则化方法.

Spectral Norm Regularization for Improving the Generalizability of Deep Learning

使用谱正则化改进深度学习的泛化性.

Understanding the Role of Individual Units in a Deep Neural Network

理解卷积神经网络中单个卷积核的作用.

High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks

从频率角度讨论卷积神经网络的泛化能力.

ECCV 2020 Tutorial：PyTorch性能调优指南

ECCV 2020 Tutorial on PyTorch Performance Tuning Guide.

Rethinking Pre-training and Self-training

对计算机视觉任务中预训练和自训练的一些讨论.