-
document
-
Smirnova, Alisa (author), Yang, J. (author), Yang, Dingqi (author), Cudre-Mauroux, Philippe (author)
Noisy labels represent one of the key issues in supervised machine learning. Existing work for label noise reduction mainly takes a probabilistic approach that infers true labels from data distributions in low-level feature spaces. Such an approach is not only limited by its capability to learn high-quality data representations, but also by...
journal article 2022
Source URL (retrieved on 2024-06-12 18:19): https://repository.tudelft.nl/islandora/search/subject%3A%22noise%255C%20reduction%22?f%5B0%5D=mods_name_personal_author_namePart_family_ss%3A%22Smirnova%22