DiscrimLoss: A Universal Loss for Hard Samples and Incorrect Samples Discrimination

21 August 2022

Papers citing "DiscrimLoss: A Universal Loss for Hard Samples and Incorrect Samples Discrimination"

4 / 4 papers shown

Title
AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss Weighting Shreyan Ganguly Roshan Nayak Rakshith Rao Ujan Deb AP Prathosh 24 1 0 11 May 2024
Guided Generation of Cause and Effect Zhongyang Li Xiao Ding Ting Liu J. E. Hu Benjamin Van Durme 155 79 0 21 Jul 2021
Combating noisy labels by agreement: A joint training method with co-regularization Hongxin Wei Lei Feng Xiangyu Chen Bo An NoLa 303 494 0 05 Mar 2020
Curriculum Loss: Robust Learning and Generalization against Label Corruption Yueming Lyu Ivor W. Tsang NoLa 47 170 0 24 May 2019