21 citations · 100 across the 21 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2021
Confidence Conditioned Knowledge Distillation
Sourav Mishra, Suresh Sundaram
In this paper, a novel confidence conditioned knowledge distillation (CCKD) scheme for transferring the knowledge from a teacher model to a student model is proposed. Existing stat…
cs.LG2021
Self Regulated Learning Mechanism for Data Efficient Knowledge Distillation
Sourav Mishra, Suresh Sundaram
Existing methods for distillation do not efficiently utilize the training data. This work presents a novel approach to perform distillation using only a subset of the training data…