Towards instance-dependent label noise-tolerant classification: a probabilistic approach
Sign Up to like & getrecommendations! Published in 2018 at "Pattern Analysis and Applications"
DOI: 10.1007/s10044-018-0750-z
Abstract: Learning from labelled data is becoming more and more challenging due to inherent imperfection of training labels. Existing label noise-tolerant learning machines were primarily designed to tackle class-conditional noise which occurs at random, independently from… read more here.
Keywords: label noise; dependent label; noise tolerant; instance dependent ... See more keywords
A Time-Consistency Curriculum for Learning From Instance-Dependent Noisy Labels
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"
DOI: 10.1109/tpami.2024.3360623
Abstract: Many machine learning algorithms are known to be fragile on simple instance-independent noisy labels. However, noisy labels in real-world data are more devastating since they are produced by more complicated mechanisms in an instance-dependent manner.… read more here.
Keywords: instance; instance dependent; curriculum; noisy labels ... See more keywords