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

TL;DR

This paper provides a comprehensive evaluation of CNNs compared to shallow methods, revealing key properties, implementation details, and the impact of data augmentation, with publicly available source code.

Contribution

It offers a rigorous comparison of CNN architectures with shallow methods, highlighting properties like dimensionality reduction and the transferability of data augmentation techniques.

Findings

CNN output dimensionality can be reduced without performance loss

Data augmentation benefits shallow methods similarly to CNNs

Deep and shallow methods share useful properties

Abstract

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.