8 citations · 17 across the 4 of their papers we have counts for
3 papers · 1 filter
A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective
Chanwoo Park, Sangdoo Yun, Sanghyuk Chun
We propose the first unified theoretical analysis of mixed sample data augmentation (MSDA), such as Mixup and CutMix. Our theoretical results show that regardless of the choice of…
REST: Performance Improvement of a Black Box Model via RL-based Spatial Transformation
Jae Myung Kim, Hyungjin Kim, Chanwoo Park +1
In recent years, deep neural networks (DNN) have become a highly active area of research, and shown remarkable achievements on a variety of computer vision tasks. DNNs, however, ar…
Sampling-based Bayesian Inference with gradient uncertainty
Chanwoo Park, Jae Myung Kim, Seok Hyeon Ha +1
Deep neural networks(NNs) have achieved impressive performance, often exceed human performance on many computer vision tasks. However, one of the most challenging issues that still…