613 citations · 1.2k across the 47 of their papers we have counts for
11 papers · 1 filter
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…
Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization
Sangwon Jung, Taeeon Park, Sanghyuk Chun +1
Many existing group fairness-aware training methods aim to achieve the group fairness by either re-weighting underrepresented groups based on certain rules or using weakly approxim…
Similarity of Neural Architectures using Adversarial Attack Transferability
Jaehui Hwang, Dongyoon Han, Byeongho Heo +3
In recent years, many deep neural architectures have been developed for image classification. Whether they are similar or dissimilar and what factors contribute to their (dis)simil…
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…
Domain Generalization by Mutual-Information Regularization with Pre-trained Models
Junbum Cha, Kyungjae Lee, Sungrae Park +1
Domain generalization (DG) aims to learn a generalized model to an unseen target domain using only limited source domains. Previous attempts to DG fail to learn domain-invariant re…
Learning Fair Classifiers with Partially Annotated Group Labels
Sangwon Jung, Sanghyuk Chun, Taesup Moon
Recently, fairness-aware learning have become increasingly crucial, but most of those methods operate by assuming the availability of fully annotated demographic group labels. We e…
Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective
Luca Scimeca, Seong Joon Oh, Sanghyuk Chun +2
Deep neural networks (DNNs) often rely on easy-to-learn discriminatory features, or cues, that are not necessarily essential to the problem at hand. For example, ducks in an image…
Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions
Michael Poli, Stefano Massaroli, Luca Scimeca +6
Effective control and prediction of dynamical systems often require appropriate handling of continuous-time and discrete, event-triggered processes. Stochastic hybrid systems (SHSs…
SWAD: Domain Generalization by Seeking Flat Minima
Junbum Cha, Sanghyuk Chun, Kyungjae Lee +4
Domain generalization (DG) methods aim to achieve generalizability to an unseen target domain by using only training data from the source domains. Although a variety of DG methods…
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…
Neural Approximation of an Auto-Regressive Process through Confidence Guided Sampling
YoungJoon Yoo, Sanghyuk Chun, Sangdoo Yun +2
We propose a generic confidence-based approximation that can be plugged in and simplify the auto-regressive generation process with a proved convergence. We first assume that the p…