← Search

Yanlin Geng

2 accepted papers

2019

Local to Global Learning: Gradually Adding Classes for Training Deep Neural Networks

CVPR 2019poster

We propose a new learning paradigm, Local to Global Learning (LGL), for Deep Neural Networks (DNNs) to improve the performance of classification problems. The core of LGL is to learn a DNN model from fewer categories (local) to more categories (global) gradually within the entire training set. LGL i…

Cited by 16PDFcodeScholar
2018

Evaluating Capability of Deep Neural Networks for Image Classification via Information Plane

ECCV 2018poster

Inspired by the pioneering work of information bottleneck principle for Deep Neural Networks (DNNs) analysis, we design an information plane based framework to evaluate the capability of DNNs for image classification tasks, which not only helps understand the capability of DNNs, but also helps us ch…

Cited by 40SourcePDFScholar