Toward Errorless Training ImageNet-1k

TL;DR

This paper presents a neural network trained on ImageNet-1k achieving 98.3% accuracy, highlighting dataset issues like duplicate images with different labels as barriers to errorless classification.

Contribution

Introduces a high-accuracy neural network trained on ImageNet-1k and discusses dataset labeling issues affecting perfection in classification.

Findings

Achieved 98.3% accuracy on ImageNet-1k

Identified dataset double-labeling as a key error source

Model uses over 322 million parameters

Abstract

In this paper, we describe a feedforward artificial neural network trained on the ImageNet 2012 contest dataset [7] with the new method of [5] to an accuracy rate of 98.3% with a 99.69 Top-1 rate, and an average of 285.9 labels that are perfectly classified over the 10 batch partitions of the dataset. The best performing model uses 322,430,160 parameters, with 4 decimal places precision. We conjecture that the reason our model does not achieve a 100% accuracy rate is due to a double-labeling problem, by which there are duplicate images in the dataset with different labels.