6 citations · 24 across the 18 of their papers we have counts for
19 papers
Rethinking Electro-Optical Vision Foundation Models for Remote Sensing Retrieval: A Controlled Comparison with Generalist VFM
Hyobin Park, Minseok Seo, Dong-Geol Choi
Vision foundation models have attracted significant attention for their ability to leverage large-scale unlabeled visual data. This advantage is particularly important in remote se…
AIS-LLM: A Unified Framework for Maritime Trajectory Prediction, Anomaly Detection, and Collision Risk Assessment with Explainable Forecasting
Hyobin Park, Jinwook Jung, Minseok Seo +4
With the increase in maritime traffic and the mandatory implementation of the Automatic Identification System (AIS), the importance and diversity of maritime traffic analysis tasks…
A Multi-In-Single-Out Network for Video Frame Interpolation without Optical Flow
Jaemin Lee, Minseok Seo, Sangwoo Lee +2
In general, deep learning-based video frame interpolation (VFI) methods have predominantly focused on estimating motion vectors between two input frames and warping them to the tar…
Improved Flood Insights: Diffusion-Based SAR to EO Image Translation
Minseok Seo, Youngtack Oh, Doyi Kim +2
Driven by rapid climate change, the frequency and intensity of flood events are increasing. Electro-Optical (EO) satellite imagery is commonly utilized for rapid response. However,…
VisDA 2022 Challenge: Domain Adaptation for Industrial Waste Sorting
Dina Bashkirova, Samarth Mishra, Diala Lteif +16
Label-efficient and reliable semantic segmentation is essential for many real-life applications, especially for industrial settings with high visual diversity, such as waste sortin…
CAFS: Class Adaptive Framework for Semi-Supervised Semantic Segmentation
Jingi Ju, Hyeoncheol Noh, Yooseung Wang +2
Semi-supervised semantic segmentation learns a model for classifying pixels into specific classes using a few labeled samples and numerous unlabeled images. The recent leading appr…
Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation
Daehan Kim, Minseok Seo, Kwanyong Park +4
Mixup provides interpolated training samples and allows the model to obtain smoother decision boundaries for better generalization. The idea can be naturally applied to the domain…
Implicit Stacked Autoregressive Model for Video Prediction
Minseok Seo, Hakjin Lee, Doyi Kim +1
Future frame prediction has been approached through two primary methods: autoregressive and non-autoregressive. Autoregressive methods rely on the Markov assumption and can achieve…
Intermediate and Future Frame Prediction of Geostationary Satellite Imagery With Warp and Refine Network
Minseok Seo, Yeji Choi, Hyungon Ry +4
Geostationary satellite imagery has applications in climate and weather forecasting, planning natural energy resources, and predicting extreme weather events. For precise and accur…
Self-Pair: Synthesizing Changes from Single Source for Object Change Detection in Remote Sensing Imagery
Minseok Seo, Hakjin Lee, Yongjin Jeon +1
For change detection in remote sensing, constructing a training dataset for deep learning models is difficult due to the requirements of bi-temporal supervision. To overcome this i…
Domain Generalization Strategy to Train Classifiers Robust to Spatial-Temporal Shift
Minseok Seo, Doyi Kim, Seungheon Shin +3
Deep learning-based weather prediction models have advanced significantly in recent years. However, data-driven models based on deep learning are difficult to apply to real-world a…
Simple Baseline for Weather Forecasting Using Spatiotemporal Context Aggregation Network
Minseok Seo, Doyi Kim, Seungheon Shin +3
Traditional weather forecasting relies on domain expertise and computationally intensive numerical simulation systems. Recently, with the development of a data-driven approach, wea…
1st Place Solution to NeurIPS 2022 Challenge on Visual Domain Adaptation
Daehan Kim, Minseok Seo, YoungJin Jeon +1
The Visual Domain Adaptation(VisDA) 2022 Challenge calls for an unsupervised domain adaptive model in semantic segmentation tasks for industrial waste sorting. In this paper, we in…
Bag of Tricks for Domain Adaptive Multi-Object Tracking
Minseok Seo, Jeongwon Ryu, Kwangjin Yoon
In this paper, SIA_Track is presented which is developed by a research team from SI Analytics. The proposed method was built from pre-existing detector and tracker under the tracki…
Source Domain Subset Sampling for Semi-Supervised Domain Adaptation in Semantic Segmentation
Daehan Kim, Minseok Seo, Jinsun Park +1
In this paper, we introduce source domain subset sampling (SDSS) as a new perspective of semi-supervised domain adaptation. We propose domain adaptation by sampling and exploiting…
Unsupervised Change Detection Based on Image Reconstruction Loss
Hyeoncheol Noh, Jingi Ju, Minseok Seo +2
To train the change detector, bi-temporal images taken at different times in the same area are used. However, collecting labeled bi-temporal images is expensive and time consuming.…
PT4AL: Using Self-Supervised Pretext Tasks for Active Learning
John Seon Keun Yi, Minseok Seo, Jongchan Park +1
Labeling a large set of data is expensive. Active learning aims to tackle this problem by asking to annotate only the most informative data from the unlabeled set. We propose a nov…
Exploiting Features with Split-and-Share Module
Jaemin Lee, Minseok Seo, Jongchan Park +1
Deep convolutional neural networks (CNNs) have shown state-of-the-art performances in various computer vision tasks. Advances on CNN architectures have focused mainly on designing…
Sequential Feature Filtering Classifier
Minseok Seo, Jaemin Lee, Jongchan Park +1
We propose Sequential Feature Filtering Classifier (FFC), a simple but effective classifier for convolutional neural networks (CNNs). With sequential LayerNorm and ReLU, FFC zeroes…