activity
20182022
most citedKnowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons

56 citations · 69 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV20225 cited

Position-aware Location Regression Network for Temporal Video Grounding

Sunoh Kim, Kimin Yun, Jin Young Choi

The key to successful grounding for video surveillance is to understand a semantic phrase corresponding to important actors and objects. Conventional methods ignore comprehensive c…

cs.CV2021

Influence-Balanced Loss for Imbalanced Visual Classification

Seulki Park, Jongin Lim, Younghan Jeon +1

In this paper, we propose a balancing training method to address problems in imbalanced data learning. To this end, we derive a new loss used in the balancing training phase that a…

cs.CV2020

AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks

Youngmin Ro, Jin Young Choi

Existing fine-tuning methods use a single learning rate over all layers. In this paper, first, we discuss that trends of layer-wise weight variations by fine-tuning using a single…

cs.CV2019

Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold

YoungJoon Yoo, Sangdoo Yun, Hyung Jin Chang +2

This paper proposes a new high dimensional regression method by merging Gaussian process regression into a variational autoencoder framework. In contrast to other regression method…

cs.CV2019

A Comprehensive Overhaul of Feature Distillation

Byeongho Heo, Jeesoo Kim, Sangdoo Yun +3

We investigate the design aspects of feature distillation methods achieving network compression and propose a novel feature distillation method in which the distillation loss is de…

cs.CV20195 cited

Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification

Youngmin Ro, Jongwon Choi, Dae Ung Jo +3

In person re-identification (ReID) task, because of its shortage of trainable dataset, it is common to utilize fine-tuning method using a classification network pre-trained on a la…