81 citations · 184 across the 17 of their papers we have counts for
10 papers · 1 filter
Sharp Stationary Gaussian Approximation for Constant-Stepsize SGD
Junghoon Seo
We prove a sharp Gaussian approximation for the invariant law of constant-stepsize SGD with bounded additive noise generated by an exogenous uniformly ergodic Markov chain. For a s…
On Pitfalls of : Data Processing Inequality Perspective
Junhwa Song, Keumgang Cha, Junghoon Seo
The RemOve-And-Retrain (ROAR) benchmark is widely used to evaluate feature attribution methods, yet its validity remains underexplored from an information-theoretic perspective. We…
Semi-Implicit Hybrid Gradient Methods with Application to Adversarial Robustness
Beomsu Kim, Junghoon Seo
Adversarial examples, crafted by adding imperceptible perturbations to natural inputs, can easily fool deep neural networks (DNNs). One of the most successful methods for training…
On the Power of Deep but Naive Partial Label Learning
Junghoon Seo, Joon Suk Huh
Partial label learning (PLL) is a class of weakly supervised learning where each training instance consists of a data and a set of candidate labels containing a unique ground truth…
Revisiting Classical Bagging with Modern Transfer Learning for On-the-fly Disaster Damage Detector
Junghoon Seo, Seungwon Lee, Beomsu Kim +1
Automatic post-disaster damage detection using aerial imagery is crucial for quick assessment of damage caused by disaster and development of a recovery plan. The main problem prev…
NL-LinkNet: Toward Lighter but More Accurate Road Extraction with Non-Local Operations
Yooseung Wang, Junghoon Seo, Taegyun Jeon
Road extraction from very high resolution satellite (VHR) images is one of the most important topics in the field of remote sensing. In this paper, we propose an efficient Non-Loca…
Bridging Adversarial Robustness and Gradient Interpretability
Beomsu Kim, Junghoon Seo, Taegyun Jeon
Adversarial training is a training scheme designed to counter adversarial attacks by augmenting the training dataset with adversarial examples. Surprisingly, several studies have o…
Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps
Beomsu Kim, Junghoon Seo, SeungHyun Jeon +3
Saliency Map, the gradient of the score function with respect to the input, is the most basic technique for interpreting deep neural network decisions. However, saliency maps are o…
Noise-adding Methods of Saliency Map as Series of Higher Order Partial Derivative
Junghoon Seo, Jeongyeol Choe, Jamyoung Koo +3
SmoothGrad and VarGrad are techniques that enhance the empirical quality of standard saliency maps by adding noise to input. However, there were few works that provide a rigorous t…
On reproduction of On the regularization of Wasserstein GANs
Junghoon Seo, Taegyun Jeon
This report has several purposes. First, our report is written to investigate the reproducibility of the submitted paper On the regularization of Wasserstein GANs (2018). Second, a…