16 citations · 31 across the 9 of their papers we have counts for
9 papers
Improving Generalization in Meta-Learning via Meta-Gradient Augmentation
Ren Wang, Haoliang Sun, Qi Wei +3
Meta-learning methods typically follow a two-loop framework, where each loop potentially suffers from notorious overfitting, hindering rapid adaptation and generalization to new ta…
Fine-Grained Classification with Noisy Labels
Qi Wei, Lei Feng, Haoliang Sun +3
Learning with noisy labels (LNL) aims to ensure model generalization given a label-corrupted training set. In this work, we investigate a rarely studied scenario of LNL on fine-gra…
EiHi Net: Out-of-Distribution Generalization Paradigm
Qinglai Wei, Beiming Yuan, Diancheng Chen
This paper develops a new EiHi net to solve the out-of-distribution (OoD) generalization problem in deep learning. EiHi net is a model learning paradigm that can be blessed on any…
Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization
Qi Wei, Haoliang Sun, Xiankai Lu +1
Sample selection is an effective strategy to mitigate the effect of label noise in robust learning. Typical strategies commonly apply the small-loss criterion to identify clean sam…
Imputing Missing Observations with Time Sliced Synthetic Minority Oversampling Technique
Andrew Baumgartner, Sevda Molani, Qi Wei +1
We present a simple yet novel time series imputation technique with the goal of constructing an irregular time series that is uniform across every sample in a data set. Specificall…
Learning to Rectify for Robust Learning with Noisy Labels
Haoliang Sun, Chenhui Guo, Qi Wei +2
Label noise significantly degrades the generalization ability of deep models in applications. Effective strategies and approaches, \textit{e.g.} re-weighting, or loss correction, a…