Publications
Principled and Efficient Transfer Learning of Deep Models via Neural Collapse
Xiao Li, Sheng Liu, Jinxin Zhou, Xinyu Lu, Carlos Fernandez-Granda, Zhihui Zhu, Qing Qu, preprint 2023.
PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels
Huaxi Huang, Hui Kang, Sheng Liu, Olivier Salvado, Thierry Rakotoarivelo, Dadong Wang, Tongliang Liu, 2023 International Conference on Computer Vision. ICCV 2023.
Avoiding spurious correlations via logit correction
Sheng Liu, Xu Zhang, Nitesh Sekhar, Yue Wu, Prateek Singhal, Carlos Fernandez-Granda The 11th International Conference on Learning Representations. ICLR 2023.
Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning
Kangning Liu, Weicheng Zhu, Yiqiu Shen, Sheng Liu, Narges Razavian, Krzysztof J. Geras, Carlos Fernandez-Granda 2023 Conference on Computer Vision and Pattern Recognition. CVPR 2023.
Generalizable deep learning model for early Alzheimer’s disease detection from structural MRIs
Sheng Liu, Arjun Masurkar, Henry Rusinek, Jingyun Chen, Ben Zhang, Weicheng Zhu, Carlos Fernandez-Granda, Narges Razavian. Nature Scientific Reports 2022.
Are All Losses Created Equal: A Neural Collapse Perspective
Jinxin Zhou, Chong You, Xiao Li, Kangning Liu, Sheng Liu, Qing Qu, Zhihui Zhu The 39th International Conference on Machine Learning. NeurIPS 2022.
Robust Training under Label Noise by Over-parameterization
Sheng Liu, Zhihui Zhu, Qing Qu, Chong You The 39th International Conference on Machine Learning. ICML 2022. (Spotlight Presentation)
Deep Probability Estimation
Sheng Liu, Aakash Kaku, Weicheng Zhu, Matan Leibovich, Sreyas Mohan (equal contribution), Boyang Yu, Laure Zanna, Narges Razavian, Carlos Fernandez-Granda The 39th International Conference on Machine Learning. ICML 2022. (Spotlight Presentation)
On Learning Contrastive Representations for Learning with Noisy Labels
Li Yi, Sheng Liu, Qi She, A Ian McLeod, Boyu Wang 2022 Conference on Computer Vision and Pattern Recognition. CVPR 2022.
Adaptive Early-Learning Correction for Segmentation from Noisy Annotations
Sheng Liu, Kangning Liu (equal contribution), Weicheng Zhu, Yiqiu Shen, Carlos Fernandez-Granda 2022 Conference on Computer Vision and Pattern Recognition. CVPR 2022. (Oral Presentation)
Development of a Deep Learning Model for Early Alzheime’s Disease Detection from Structural MRIs and External Validation on an Independent Cohort
Sheng Liu, Arjun Masurkar, Henry Rusinek, Jingyun Chen, Ben Zhang, Weicheng Zhu, Carlos Fernandez-Granda, Narges Razavian. preprint.
Convolutional normalization: Improving deep convolutional network robustness and training
Sheng Liu, Xiao Li (equal contribution), Yuexiang Zhai, Chong You, Zhihui Zhu, Carlos Fernandez-Granda, Qing Qu The 35th Conference on Neural Information Processing Systems. NeurIPS 2021.
Early-learning regularization prevents memorization of noisy labels
Sheng Liu, Jonathan Niles-Weed, Narges Razavian, Carlos Fernandez-Granda. . The 34th Conference on Neural Information Processing Systems. NeurIPS 2020.
On the design of convolutional neural networks for automatic detection of Alzheimer’s disease
Sheng Liu, Chhavi Yadav, Carlos Fernandez-Granda, Narges Razavian 2019 NeurIPS Machine Learning for Health Workshop. NeurIPS 2019. (Best Paper Award Honorable Mention)
Sparse recovery beyond compressed sensing: Separable nonlinear inverse problems
Brett Bernstein, Sheng Liu, Chrysa Papadaniil, Carlos Fernandez-Granda. IEEE transactions on information theory.
Time-Series Analysis via Low-Rank Matrix Factorization Applied to Infant-Sleep Data
Sheng Liu, Mark Cheng, Hayley Brooks, Wayne Mackey, David J Heeger, Esteban G Tabak, Carlos Fernandez-Granda NeurIPS 2019 workshop on machine learning for healthcare. NeurIPS 2019.