32 citations · 73 across the 10 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2022★ 11 cited
Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation
Minsoo Kang, Jaeyoo Park, Bohyung Han
We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous ta…
cs.LG2020★ 32 cited
Operation-Aware Soft Channel Pruning using Differentiable Masks
Minsoo Kang, Bohyung Han
We propose a simple but effective data-driven channel pruning algorithm, which compresses deep neural networks in a differentiable way by exploiting the characteristics of operatio…
cs.LG2019★ 5 cited
Towards Oracle Knowledge Distillation with Neural Architecture Search
Minsoo Kang, Jonghwan Mun, Bohyung Han
We present a novel framework of knowledge distillation that is capable of learning powerful and efficient student models from ensemble teacher networks. Our approach addresses the…