Search Results for author: Junghoon Seo

Found 19 papers, 9 papers with code

Prototype-oriented Unsupervised Change Detection for Disaster Management

no code implementations15 Oct 2023 Youngtack Oh, Minseok Seo, Doyi Kim, Junghoon Seo

Climate change has led to an increased frequency of natural disasters such as floods and cyclones.

Change Detection Management

Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer

no code implementations12 May 2023 Hakjin Lee, Minki Song, Jamyoung Koo, Junghoon Seo

The Detection Transformer (DETR) has emerged as a pivotal role in object detection tasks, setting new performance benchmarks due to its end-to-end design and scalability.

object-detection Object Detection In Aerial Images +1

On Pitfalls of $\textit{RemOve-And-Retrain}$: Data Processing Inequality Perspective

1 code implementation26 Apr 2023 Junhwa Song, Keumgang Cha, Junghoon Seo

Approaches for appraising feature importance approximations, alternatively referred to as attribution methods, have been established across an extensive array of contexts.

Benchmarking Feature Importance

A Billion-scale Foundation Model for Remote Sensing Images

no code implementations11 Apr 2023 Keumgang Cha, Junghoon Seo, Taekyung Lee

Recently, research in the remote sensing field has focused primarily on the pretraining method and the size of the dataset, with limited emphasis on the number of model parameters.

object-detection Object Detection In Aerial Images +1

Implicit Stacked Autoregressive Model for Video Prediction

1 code implementation14 Mar 2023 Minseok Seo, Hakjin Lee, Doyi Kim, Junghoon Seo

Future frame prediction has been approached through two primary methods: autoregressive and non-autoregressive.

Video Prediction Weather Forecasting

Self-Pair: Synthesizing Changes from Single Source for Object Change Detection in Remote Sensing Imagery

1 code implementation20 Dec 2022 Minseok Seo, Hakjin Lee, Yongjin Jeon, Junghoon Seo

For change detection in remote sensing, constructing a training dataset for deep learning models is difficult due to the requirements of bi-temporal supervision.

Change Detection

Semi-Implicit Hybrid Gradient Methods with Application to Adversarial Robustness

no code implementations21 Feb 2022 Beomsu Kim, Junghoon Seo

Adversarial examples, crafted by adding imperceptible perturbations to natural inputs, can easily fool deep neural networks (DNNs).

Adversarial Robustness

Contrastive Multiview Coding with Electro-optics for SAR Semantic Segmentation

no code implementations31 Aug 2021 Keumgang Cha, Junghoon Seo, Yeji Choi

In the training of deep learning models, how the model parameters are initialized greatly affects the model performance, sample efficiency, and convergence speed.

Representation Learning Semantic Segmentation

Training Domain-invariant Object Detector Faster with Feature Replay and Slow Learner

1 code implementation31 May 2021 Chaehyeon Lee, Junghoon Seo, Heechul Jung

In deep learning-based object detection on remote sensing domain, nuisance factors, which affect observed variables while not affecting predictor variables, often matters because they cause domain changes.

object-detection Object Detection

On the Power of Deep but Naive Partial Label Learning

1 code implementation22 Oct 2020 Junghoon Seo, Joon Suk Huh

We also address the question of how and why such a naive model works well with deep neural networks.

Partial Label Learning Weakly-supervised Learning

Revisiting Classical Bagging with Modern Transfer Learning for On-the-fly Disaster Damage Detector

no code implementations4 Oct 2019 Junghoon Seo, Seungwon Lee, Beomsu Kim, Taegyun Jeon

In this paper, we revisit the classical bootstrap aggregating approach in the context of modern transfer learning for data-efficient disaster damage detection.

Change Detection Disentanglement +3

Deep Closed-Form Subspace Clustering

no code implementations26 Aug 2019 Junghoon Seo, Jamyoung Koo, Taegyun Jeon

We propose Deep Closed-Form Subspace Clustering (DCFSC), a new embarrassingly simple model for subspace clustering with learning non-linear mapping.


NL-LinkNet: Toward Lighter but More Accurate Road Extraction with Non-Local Operations

1 code implementation22 Aug 2019 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.

Road Segmentation

Bridging Adversarial Robustness and Gradient Interpretability

1 code implementation27 Mar 2019 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.

Adversarial Robustness Test

Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps

2 code implementations13 Feb 2019 Beomsu Kim, Junghoon Seo, SeungHyun Jeon, Jamyoung Koo, Jeongyeol Choe, Taegyun Jeon

Saliency Map, the gradient of the score function with respect to the input, is the most basic technique for interpreting deep neural network decisions.

Domain Adaptive Generation of Aircraft on Satellite Imagery via Simulated and Unsupervised Learning

no code implementations8 Jun 2018 Junghoon Seo, Seunghyun Jeon, Taegyun Jeon

Object detection and classification for aircraft are the most important tasks in the satellite image analysis.

BIG-bench Machine Learning Classification +3

Noise-adding Methods of Saliency Map as Series of Higher Order Partial Derivative

no code implementations8 Jun 2018 Junghoon Seo, Jeongyeol Choe, Jamyoung Koo, Seunghyeon Jeon, Beomsu Kim, Taegyun Jeon

SmoothGrad and VarGrad are techniques that enhance the empirical quality of standard saliency maps by adding noise to input.

Cannot find the paper you are looking for? You can Submit a new open access paper.