Improving Transferability of Deep Neural Networks

07/30/2018
by   Parijat Dube, et al.
8

Learning from small amounts of labeled data is a challenge in the area of deep learning. This is currently addressed by Transfer Learning where one learns the small data set as a transfer task from a larger source dataset. Transfer Learning can deliver higher accuracy if the hyperparameters and source dataset are chosen well. One of the important parameters is the learning rate for the layers of the neural network. We show through experiments on the ImageNet22k and Oxford Flowers datasets that improvements in accuracy in range of 127 the images/label parameter for a dataset can potentially be used to determine optimal learning rates for the layers to get the best overall accuracy. We additionally validate this method on a sample of real-world image classification tasks from a public visual recognition API.

READ FULL TEXT

page 4

page 6

page 7

page 12

page 13

research
04/02/2019

Lautum Regularization for Semi-supervised Transfer Learning

Transfer learning is a very important tool in deep learning as it allows...
research
11/05/2018

Transfer learning for time series classification

Transfer learning for deep neural networks is the process of first train...
research
06/19/2022

Agricultural Plantation Classification using Transfer Learning Approach based on CNN

Hyper-spectral images are images captured from a satellite that gives sp...
research
06/26/2020

Ensemble Transfer Learning for Emergency Landing Field Identification on Moderate Resource Heterogeneous Kubernetes Cluster

The full loss of thrust of an aircraft requires fast and reliable decisi...
research
05/12/2020

Modularizing Deep Learning via Pairwise Learning With Kernels

By redefining the conventional notions of layers, we present an alternat...
research
01/19/2018

A Practitioners' Guide to Transfer Learning for Text Classification using Convolutional Neural Networks

Transfer Learning (TL) plays a crucial role when a given dataset has ins...
research
02/02/2022

Auto-Transfer: Learning to Route Transferrable Representations

Knowledge transfer between heterogeneous source and target networks and ...

Please sign up or login with your details

Forgot password? Click here to reset