Some Improvements on Deep Convolutional Neural Network Based Image Classification

TL;DR

This paper presents techniques to enhance deep convolutional neural networks for image classification, achieving significant accuracy improvements in the ImageNet challenge by data augmentation, test-time transformations, and model ensembling.

Contribution

The paper introduces specific data augmentation and model combination strategies that significantly improve CNN performance on large-scale image classification.

Findings

Achieved a top 5 error rate of 13.55% on ImageNet without external data.

Over 20% relative improvement over previous year's winner.

Enhanced accuracy through multiple image transformations and model ensembling.

Abstract

We investigate multiple techniques to improve upon the current state of the art deep convolutional neural network based image classification pipeline. The techiques include adding more image transformations to training data, adding more transformations to generate additional predictions at test time and using complementary models applied to higher resolution images. This paper summarizes our entry in the Imagenet Large Scale Visual Recognition Challenge 2013. Our system achieved a top 5 classification error rate of 13.55% using no external data which is over a 20% relative improvement on the previous year's winner.