Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation

arXiv:2305.19486v2 Announce Type: replace
Abstract: Deep learning faces a formidable challenge when handling noisy labels, as models tend to overfit samples affected by label noise. This challenge is further compounded by the presence of instance-dependent noise (IDN), a realistic form of label noise arising from ambiguous sample information. To address IDN, Label Noise Learning (LNL) incorporates a sample selection stage to differentiate clean and noisy-label samples. This stage uses an arbitrary criterion and a pre-defined curriculum that initially selects most …

abstract arxiv challenge cs.cv deep learning form information instance labels noise rate sample samples type