instance-dependent noise原理 Instance-Dependent Noise (IDN)是一种处理噪声标签的策略,其原理基于假设在真实标签y给定时,noise标签y¯和输入的特征x是相关的。具体来说,IDN利用DNN(深度神经网络)在没有label noise的数据集上训练的过程,将DNN中较难训练的实例和类联系起来,从而计算误标记的得分和潜在的noisy ...
原论文标题:Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise 问题引入: 以往对于Label noise的研究大多基于class-conditional noise(CCN)假设,即假设noise标签 y¯ 是与输入的特征 x 无关的,而作者认为这样的假设不符合实际:在Clothing1M真实噪音数据集上进行的计算...
如何让模型对instance-dependent label noise 鲁棒不仅在技术上存在着比较多的难题,在理论上也不好建模(和instance-independent相比)。 我们的贡献是提供一个instance-dependent label noise的解决方案并提供最优性的保证。基于自步学习+双网络互相学习(co-teaching)的策略在筛选instance-independent噪音标签上已经比较成熟,...
Instance-dependent label noiseClassificationLogistic regressionLearning from labelled data is becoming more and more challenging due to inherent imperfection of training labels. Existing label noise-tolerant learning machines were primarily designed to tackle class-conditional noise which occurs at random, ...
@inproceedings{chen2021beyond, title={Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise.}, author={Chen, Pengfei and Ye, Junjie and Chen, Guangyong and Zhao, Jingwei and Heng, Pheng-Ann}, booktitle={Proceedings of the AAAI Conference on Artificial In...
Human-annotated labels are often prone to noise, and the presence of such noise will degrade the performance of the resulting deep neural network (DNN) models. Much of the literature (with several recent exceptions) of learning with noisy labels focuses on the case when the label noise is ind...
This code is a PyTorch implementation of our paper "Learning with Instance-Dependent Label Noise: A Sample Sieve Approach" accepted by ICLR2021. The code is run on the Tesla V-100. Prerequisites Python 3.6.9 PyTorch 1.2.0 Torchvision 0.5.0 ...
To alleviate the issues, we introduce typicality- and instance-dependent label noise (TIDN) to simulate real-world noise and establish a TIDN-combating framework to combat label noise. Specifically, we use the sample's distance to decision boundaries in the feature space to represent typicality....
Part-dependent Label Noise: Towards Instance-dependent Label NoiseBo HanDacheng TaoGang NiuHaifeng LiuMasashi SugiyamaMingming GongNannan WangTongliang LiuXiaobo Xia
Learning with Instance-Dependent Label Noise: A Sample Sieve ApproachHao ChengZhaowei ZhuXingyu LiYifei GongXing SunYang LiuInternational Conference on Learning Representations