Regularization on augmented data to diversify sparse representation for robust image classification

S Zeng, B Zhang, J Gou, Y Xu - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Image classification is a fundamental component in modern computer vision systems, where
sparse representation-based classification has drawn a lot of attention due to its robustness …

Doubly stochastic models: Learning with unbiased label noises and inference stability

H **ong, X Li, B Yu, Z Zhu, D Wu, D Dou - arxiv preprint arxiv:2304.00320, 2023 - arxiv.org
Random label noises (or observational noises) widely exist in practical machine learning
settings. While previous studies primarily focus on the affects of label noises to the …

Stochastic gradient descent with random label noises: doubly stochastic models and inference stabilizer

H **ong, X Li, B Yu, D Wu, Z Zhu… - … Learning: Science and …, 2024 - iopscience.iop.org
Random label noise (or observational noise) widely exists in practical machine learning
settings. While previous studies primarily focused on the effects of label noise to the …

Implicit regularization effects of unbiased random label noises with SGD

H **ong, X Li, B Yu, D Dou, D Wu, Z Zhu - 2021 - openreview.net
Random label noises (or observational noises) widely exist in practical machinelearning
settings. we analyze the learning dynamics of stochastic gradient descent (SGD) over the …