The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective

10 October 2022

Papers citing "The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective"

7 / 7 papers shown

Title
LatentDR: Improving Model Generalization Through Sample-Aware Latent Degradation and Restoration Ran Liu Sahil Khose Jingyun Xiao Lakshmi Sathidevi Keerthan Ramnath Z. Kira Eva L. Dyer 19 3 0 28 Aug 2023
Mitigating multiple descents: A model-agnostic framework for risk monotonization Pratik V. Patil Arun K. Kuchibhotla Yuting Wei Alessandro Rinaldo 24 8 0 25 May 2022
The Implicit Bias of Benign Overfitting Ohad Shamir 91 35 0 27 Jan 2022
Masked Autoencoders Are Scalable Vision Learners Kaiming He Xinlei Chen Saining Xie Yanghao Li Piotr Dollár Ross B. Girshick ViT TPM 258 7,412 0 11 Nov 2021
Harmless interpolation in regression and classification with structured features Andrew D. McRae Santhosh Karnik Mark A. Davenport Vidya Muthukumar 93 11 0 09 Nov 2021
Learning with invariances in random features and kernel models Song Mei Theodor Misiakiewicz Andrea Montanari OOD 44 89 0 25 Feb 2021
Negative Data Augmentation Abhishek Sinha Kumar Ayush Jiaming Song Burak Uzkent Hongxia Jin Stefano Ermon 29 72 0 09 Feb 2021