5 citations · 11 across the 8 of their papers we have counts for
Showing 2023Show all
3 papers · 1 filter
cs.CV2023★ 5 cited
Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition
Shuoyuan Wang, Jindong Wang, HuaJun Xi +3
Human Activity Recognition (HAR) models often suffer from performance degradation in real-world applications due to distribution shifts in activity patterns across individuals. Tes…
cs.LG2023
Conformal Prediction for Deep Classifier via Label Ranking
Jianguo Huang, Huajun Xi, Linjun Zhang +3
Conformal prediction is a statistical framework that generates prediction sets containing ground-truth labels with a desired coverage guarantee. The predicted probabilities produce…
cs.LG2023★ 5 cited
Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
Hao Chen, Jindong Wang, Ankit Shah +5
Pre-training on large-scale datasets and then fine-tuning on downstream tasks have become a standard practice in deep learning. However, pre-training data often contain label noise…