16 citations · 37 across the 25 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.CV2017★ 15 cited
Knowledge distillation using unlabeled mismatched images
Mandar Kulkarni, Kalpesh Patil, Shirish Karande
Current approaches for Knowledge Distillation (KD) either directly use training data or sample from the training data distribution. In this paper, we demonstrate effectiveness of '…
cs.LG2017★ 16 cited
Layer-wise training of deep networks using kernel similarity
Mandar Kulkarni, Shirish Karande
Deep learning has shown promising results in many machine learning applications. The hierarchical feature representation built by deep networks enable compact and precise encoding…