Noise against noise: stochastic label noise helps combat inherent label noise

Authors: Pengfei Chen, Guangyong Chen, Junjie Ye, jingwei zhao, Pheng-Ann Heng

ICLR 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We comprehensively verify the utility of SLN on different types of label noise, including symmetric noise, asymmetric noise (Zhang & Sabuncu, 2018), instance-dependent noise (Chen et al., 2020a) and open-set noise (Wang et al., 2018) synthesized on CIFAR-10 and CIFAR-100 and real-world noise on Clothing1M (Xiao et al., 2015).
Researcher Affiliation Collaboration Pengfei Chen1, Guangyong Chen2 , Junjie Ye3 , Jingwei Zhao3, Pheng-Ann Heng1,2 1The Chinese University of Hong Kong 2Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences 3VIVO AI Lab
Pseudocode No The paper does not contain any explicitly labeled 'Pseudocode' or 'Algorithm' blocks.
Open Source Code Yes Our code is released1. 1https://github.com/chenpf1025/SLN
Open Datasets Yes We comprehensively verify the utility of SLN on different types of label noise, including symmetric noise, asymmetric noise (Zhang & Sabuncu, 2018), instance-dependent noise (Chen et al., 2020a) and open-set noise (Wang et al., 2018) synthesized on CIFAR-10 and CIFAR-100 and real-world noise on Clothing1M (Xiao et al., 2015).
Dataset Splits Yes We use 5k noisy samples as the validation to tune hyperparameters, then train the model on the full training set and report the test accuracy at the last epoch. ... Clothing1M (Xiao et al., 2015) is a large-scale benchmark of clothing images from online shops with 14 classes, containing real-world label noise. It has 1 million noisy samples for training, 14k and 10k clean samples for validation and test.
Hardware Specification Yes We mark the top-3 results in bold and present the average training time of each method, evaluated on a single V100 GPU.
Software Dependencies No The paper mentions using the 'SGD optimizer' and 'Imagenet-pretrained ResNet-50' but does not provide specific version numbers for any software libraries, frameworks (e.g., PyTorch, TensorFlow), or programming languages used.
Experiment Setup Yes In all experiments on CIFAR-10 and CIFAR-100, we train wide ResNet-28-2 (Zagoruyko & Komodakis, 2016) for 300 epochs using the SGD optimizer with learning rate 0.001, momentum 0.9, weight decay 5e-4, and a batchsize of 128. ... On CIFAR-10, we use σ = 1 for symmetric noise and σ = 0.5 otherwise; On CIFAR-100, we use σ = 0.1 for instance-dependent noise and σ = 0.2 otherwise.