“…In this section, we compared our method to most recent state-of-the-art methods: DivideMix (Li et al, 2020a), LossModelling (Arazo et al, 2019), Coteaching+ (Yu et al, 2019), Mixup (Zhang et al, 2017), F-correction (Patrini et al, 2017), SELFIE (Song et al, 2019), PLC (Zhang et al, 2021), PENCIL (Yi and Wu, 2019), ELR (Liu et al, 2020a), NCT , MOIT+ (Ortego et al, 2021), NGC , RRL (Li et al, 2020b), FaMUS , GJS (Ghosh and Lan, 2021), PDLC (Liu et al, 2020b). We show, that the proposed method achieves consistent improvements in all datasets and at all noise types and ratios.…”