Ranking-based-Instance-Selection
Code for the article "Confidence Scores Make Instance-dependent Label-noise Learning Possible", ICML'21
Github repo for webly labeled learning of sound events
A Light CNN for Deep Face Representation with Noisy Labels, TIFS 2018
π§Ή Formerly for binary classification with noisy labels. Replaced by cleanlab.
The main features of cgnorthcutt/rankpruning are: Robust Learning Frameworks.
Open-source alternatives to cgnorthcutt/rankpruning include: alibaba-edu/ranking-based-instance-selection β Ranking-based-Instance-Selection. antoninbrthn/csidn β Code for the article "Confidence Scores Make Instance-dependent Label-noise Learning Possible", ICML'21. anuragkr90/webly-labeled-sounds β Github repo for webly labeled learning of sound events. arghosh/robustmw-net β WACV'21: Do We Really Need Gold Samples for Sample Weighting Under Label Noise? automl-4paradigm/s2e β Q. Yao, H. Yang, B. Han, G. Niu, J. Kwok. Searching to Exploit Memorization Effect in Learning from Noisy Labels. ICMLβ¦ alfredxiangwu/lightcnn β A Light CNN for Deep Face Representation with Noisy Labels, TIFS 2018.