activity
20192022
most citedAre All Losses Created Equal: A Neural Collapse Perspective

8 citations · 8 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CV2022

PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels

Huaxi Huang, Hui Kang, Sheng Liu +4

Convolutional Neural Networks (CNNs) have demonstrated superiority in learning patterns, but are sensitive to label noises and may overfit noisy labels during training. The early s…

cs.LG20228 cited

Are All Losses Created Equal: A Neural Collapse Perspective

Jinxin Zhou, Chong You, Xiao Li +4

While cross entropy (CE) is the most commonly used loss to train deep neural networks for classification tasks, many alternative losses have been developed to obtain better empiric…

cs.LG2020

Early-Learning Regularization Prevents Memorization of Noisy Labels

Sheng Liu, Jonathan Niles-Weed, Narges Razavian +1

We propose a novel framework to perform classification via deep learning in the presence of noisy annotations. When trained on noisy labels, deep neural networks have been observed…

eess.IV2019

On the design of convolutional neural networks for automatic detection of Alzheimer's disease

Sheng Liu, Chhavi Yadav, Carlos Fernandez-Granda +1

Early detection is a crucial goal in the study of Alzheimer's Disease (AD). In this work, we describe several techniques to boost the performance of 3D deep convolutional neural ne…

eess.SP2019

Sparse Recovery Beyond Compressed Sensing: Separable Nonlinear Inverse Problems

Brett Bernstein, Sheng Liu, Chrysa Papadaniil +1

Extracting information from nonlinear measurements is a fundamental challenge in data analysis. In this work, we consider separable inverse problems, where the data are modeled as…

stat.ML2019

Time-Series Analysis via Low-Rank Matrix Factorization Applied to Infant-Sleep Data

Sheng Liu, Mark Cheng, Hayley Brooks +4

We propose a nonparametric model for time series with missing data based on low-rank matrix factorization. The model expresses each instance in a set of time series as a linear com…