用新方法训练神经网络，图像分类准确率达98.3%
Toward Errorless Training ImageNet-1k
- 采用新方法在ImageNet-12上训练，实现98.3%准确率
- 每批次平均285.9个标签完全正确，最高达99.69% Top-1
- 模型含3.2亿参数，适合研究数据标注误差影响
本文描述了一个基于ImageNet 2012竞赛数据集[7]的前馈人工神经网络，采用[5]中的新方法训练，达到98.3%的准确率，其中Top-1准确率为99.69%，在数据集10个批次分区中，平均有285.9个标签被完美分类。表现最佳的模型包含322,430,160个参数，使用4位小数精度。我们推测模型未能达到100%准确率的原因是数据集中存在双标签问题——即同一图像被赋予不同标签。该问题可能源于重复图像在标注时出现不一致。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。