ML p(r)ior | Transfer Learning Based on AdaBoost for Feature Selection from Multiple ConvNet Layer Features

Transfer Learning Based on AdaBoost for Feature Selection from Multiple ConvNet Layer Features

2016-02-01
Convolutional Networks (ConvNets) are powerful models that learn hierarchies of visual features, which could also be used to obtain image representations for transfer learning. The basic pipeline for transfer learning is to first train a ConvNet on a large dataset (source task) and then use feed-forward units activation of the trained ConvNet as image representation for smaller datasets (target task). Our key contribution is to demonstrate superior performance of multiple ConvNet layer features over single ConvNet layer features. Combining multiple ConvNet layer features will result in more complex feature space with some features being repetitive. This requires some form of feature selection. We use AdaBoost with single stumps to implicitly select only distinct features that are useful towards classification from concatenated ConvNet features. Experimental results show that using multiple ConvNet layer activation features instead of single ConvNet layer features consistently will produce superior performance. Improvements becomes significant as we increase the distance between source task and the target task.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2014-09-04
1409.1556 | cs.CV

In this work we investigate the effect of the convolutional network depth on its accuracy in the lar… show more
PDF

Highlights - Most important sentences from the article

2013-11-12
1311.2901 | cs.CV

Large Convolutional Network models have recently demonstrated impressive classification performance … show more
PDF

Highlights - Most important sentences from the article

2013-10-06

We evaluate whether features extracted from the activation of a deep convolutional network trained i… show more
PDF

Highlights - Most important sentences from the article

2014-03-23

Recent results indicate that the generic descriptors extracted from the convolutional neural network… show more
PDF

Highlights - Most important sentences from the article

2016-11-16

We propose Deep Feature Interpolation (DFI), a new data-driven baseline for automatic high-resolutio… show more
PDF

Highlights - Most important sentences from the article

2016-03-30
1603.09246 | cs.CV

In this paper we study the problem of image representation learning without human annotation. By fol… show more
PDF

Highlights - Most important sentences from the article

2018-03-21

Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of com… show more
PDF

Highlights - Most important sentences from the article

2014-11-27

A number of recent studies have shown that a Deep Convolutional Neural Network (DCNN) pretrained on … show more
PDF

Highlights - Most important sentences from the article

2018-02-21

Deep convolutional neural networks provide a powerful feature learning capability for image classifi… show more
PDF

Highlights - Most important sentences from the article

2018-03-08
1803.03310 | cs.CV

This work studies deep metric learning under small to medium scale data as we believe that better ge… show more
PDF

Highlights - Most important sentences from the article

2019-04-04
1904.02322 | cs.CV

Deep neural networks have been widely used in computer vision. There are several well trained deep n… show more
PDF

Highlights - Most important sentences from the article

2016-11-06

Convolutional Neural Networks (ConvNets) have achieved excellent recognition performance in various … show more
PDF

Highlights - Most important sentences from the article

2017-04-18
1704.05310 | stat.ML

Convolutional neural networks provide visual features that perform remarkably well in many computer … show more
PDF

Highlights - Most important sentences from the article

2014-11-06

Many deep neural networks trained on natural images exhibit a curious phenomenon in common: on the f… show more
PDF

Highlights - Most important sentences from the article

2017-02-28
1702.08690 | cs.CV

Deep neural networks require a large amount of labeled training data during supervised learning. How… show more
PDF

Highlights - Most important sentences from the article