activity
20182026
most citedKnowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons

56 citations · 139 across the 13 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

On-Policy Delta Distillation

Byeongho Heo, Jaehui Hwang, Sangdoo Yun +1

On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervisio…

cs.LG2025

DNNs May Determine Major Properties of Their Outputs Early, with Timing Possibly Driven by Bias

Song Park, Sanghyuk Chun, Byeongho Heo +1

This paper argues that deep neural networks (DNNs) mostly determine their outputs during the early stages of inference, where biases inherent in the model play a crucial role in sh…

cs.LG20219 cited

Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching

Mingi Ji, Byeongho Heo, Sungrae Park

Knowledge distillation extracts general knowledge from a pre-trained teacher network and provides guidance to a target student network. Most studies manually tie intermediate featu…

cs.LG2020

AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights

Byeongho Heo, Sanghyuk Chun, Seong Joon Oh +5

Normalization techniques are a boon for modern deep learning. They let weights converge more quickly with often better generalization performances. It has been argued that the norm…

cs.LG201856 cited

Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons

Byeongho Heo, Minsik Lee, Sangdoo Yun +1

An activation boundary for a neuron refers to a separating hyperplane that determines whether the neuron is activated or deactivated. It has been long considered in neural networks…

cs.LG2018

Knowledge Distillation with Adversarial Samples Supporting Decision Boundary

Byeongho Heo, Minsik Lee, Sangdoo Yun +1

Many recent works on knowledge distillation have provided ways to transfer the knowledge of a trained network for improving the learning process of a new one, but finding a good te…