Toward Errorless Training ImageNet-1k
This work addresses the challenge of reducing errors in large-scale image classification for computer vision researchers, though it appears incremental as it builds on existing methods.
The paper tackled the problem of achieving near-perfect accuracy on ImageNet-1k by training a feedforward neural network, resulting in a 98.3% accuracy rate and 99.69 Top-1 rate, with an average of 285.9 perfectly classified labels across dataset partitions.
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.