20 citations · 81 across the 16 of their papers we have counts for
Showing 2022 · cs.CVShow all
2 papers · 2 filters
cs.CV2022★ 4 cited
Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels
Kai Wang, Xiangyu Peng, Shuo Yang +4
Learning with noisy labels has aroused much research interest since data annotations, especially for large-scale datasets, may be inevitably imperfect. Recent approaches resort to…
cs.CV2022★ 11 cited
Crafting Better Contrastive Views for Siamese Representation Learning
Xiangyu Peng, Kai Wang, Zheng Zhu +2
Recent self-supervised contrastive learning methods greatly benefit from the Siamese structure that aims at minimizing distances between positive pairs. For high performance Siames…