Zedong Chu (储泽栋)

Zedong Chu (储泽栋)

Alibaba | UCL | BJTU

深度学习 训练集与验证集损失分析

less than 1 minute read

Published:

深度学习中，如何对训练集与验证集上的Loss变化进行正确的分析，并进行妥当的改善？

训练集损失下降 验证集损失下降 ——> 网络正在学习（理想状态）

训练集损失下降 验证集损失不变 ——> 网络过拟合（尝试dropout、L2等手段）

训练集损失不变 验证集损失下降 ——> 数据集有问题（检查数据集）

训练集损失不变 验证集损失不变 ——> 网络遇到学习瓶颈（减小learning rate或batch size）

训练集损失上升 验证集损失上升 ——> 网络结构设计不当、超参设置不当、数据集经过清洗等

You May Also Enjoy

Image Classification Based on Few-Shot Learning

39 minute read

Published:

This blog classifies and summarizes the current image classification algorithms based on Few-shot learning. According to the modeling methods of different data types, Few-shot image classification algorithms are divided into convolution neural network model and graph neural network model. Convolution neural network model is divided into four learning paradigms: transfer learning, meta learning, Bayesian learning and dual learning. Two kinds of algorithms are introduced in detail. Finally, for the current Few-shot image classification algorithm, we discuss the ethical oriented implications in terms of interpretability and privacy.

Temporal action localization with Semi-Supervised Learning

8 minute read

Published:

Temporal action localization is an important task in the field of video content analysis, and its goal is to locate the action instances with precise boundaries and flexible intervals in an untrimmed video. Constructing a large enough data set that contains video clips and annotations will require vast human effort. Since there are quite many unlabeled videos on the internet, it is worth trying to combine semi-supervised approaches into temporal action localization task.

探秘计算机视觉中的注意力机制

1 minute read

Published:

近年来，越来越多的工作专注于将注意力机制融入计算机视觉任务中。本文重点介绍注意力机制的基本原理和利用飞桨实现注意力机制的基本方法。