Icing on the Cake: An Easy and Quick Post-Learnig Method You Can Try After Deep Learning

07/17/2018
by   Tomohiko Konno, et al.
0

We found an easy and quick post-learning method named "Icing on the Cake" to enhance a classification performance in deep learning. The method is that we train only the final classifier again after an ordinary training is done.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/09/2019

Exposure Interpolation Via Fusing Conventional and Deep Learning Methods

Deep learning based methods have penetrated many image processing proble...
research
09/12/2021

An Unsupervised Deep-Learning Method for Fingerprint Classification: the CCAE Network and the Hybrid Clustering Strategy

The fingerprint classification is an important and effective method to q...
research
05/22/2018

Training Convolutional Networks with Web Images

In this thesis we investigate the effect of using web images to build a ...
research
08/23/2022

Why Deep Learning's Performance Data Are Misleading

This is a theoretical paper, as a companion paper of the keynote talk at...
research
09/19/2023

Decoupled Training: Return of Frustratingly Easy Multi-Domain Learning

Multi-domain learning (MDL) aims to train a model with minimal average r...
research
02/05/2019

Deep Learning for Bridge Load Capacity Estimation in Post-Disaster and -Conflict Zones

Many post-disaster and -conflict regions do not have sufficient data on ...
research
04/02/2019

Generative-Discriminative Complementary Learning

Majority of state-of-the-art deep learning methods for vision applicatio...

Please sign up or login with your details

Forgot password? Click here to reset