Return of the Devil in the Details: Delving Deep into Convolutional Nets

05/14/2014
by   Ken Chatfield, et al.
0

The latest generation of Convolutional Neural Networks (CNN) have achieved impressive results in challenging benchmarks on image recognition and object detection, significantly raising the interest of the community in these methods. Nevertheless, it is still unclear how different CNN methods compare with each other and with previous state-of-the-art shallow representations such as the Bag-of-Visual-Words and the Improved Fisher Vector. This paper conducts a rigorous evaluation of these new techniques, exploring different deep architectures and comparing them on a common ground, identifying and disclosing important implementation details. We identify several useful properties of CNN-based representations, including the fact that the dimensionality of the CNN output layer can be reduced significantly without having an adverse effect on performance. We also identify aspects of deep and shallow methods that can be successfully shared. In particular, we show that the data augmentation techniques commonly applied to CNN-based methods can also be applied to shallow methods, and result in an analogous performance boost. Source code and models to reproduce the experiments in the paper is made publicly available.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/09/2015

When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition

Deep learning, in particular Convolutional Neural Network (CNN), has ach...
research
03/23/2018

Object Detection for Comics using Manga109 Annotations

With the growth of digitized comics, image understanding techniques are ...
research
09/27/2018

CNN Based Posture-Free Hand Detection

Although many studies suggest high performance hand detection methods, t...
research
04/13/2015

Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction

Object detection systems based on the deep convolutional neural network ...
research
04/12/2022

Back to the Roots: Reconstructing Large and Complex Cranial Defects using an Image-based Statistical Shape Model

Designing implants for large and complex cranial defects is a challengin...
research
12/27/2017

Learning More Universal Representations for Transfer-Learning

Transfer learning is commonly used to address the problem of the prohibi...
research
11/21/2014

Understanding image representations by measuring their equivariance and equivalence

Despite the importance of image representations such as histograms of or...

Please sign up or login with your details

Forgot password? Click here to reset