Some Improvements on Deep Convolutional Neural Network Based Image Classification
This work provides incremental improvements for computer vision researchers and practitioners in image classification tasks.
The paper tackled image classification by improving a deep convolutional neural network pipeline, achieving a top-5 error rate of 13.55% on ImageNet 2013, which is a 20% relative improvement over the previous year's winner.
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.