Jaejun Yoo
YOU?
Author Swipe
View article: PCCP: A prefetched fingerprint data‐based continuous convergence positioning framework for performance improvement in urban environments
PCCP: A prefetched fingerprint data‐based continuous convergence positioning framework for performance improvement in urban environments Open
Positioning systems play a critical role in urban environments, where accurately determining a user's location is essential for a wide range of applications. Managing vast and diverse datasets such as Wi‐Fi, Bluetooth, and image‐based fing…
View article: Deep learning enhances reliability of dynamic contrast-enhanced MRI in diffuse gliomas: bypassing post-processing and providing uncertainty maps
Deep learning enhances reliability of dynamic contrast-enhanced MRI in diffuse gliomas: bypassing post-processing and providing uncertainty maps Open
Objectives To propose and evaluate a novel deep learning model for directly estimating pharmacokinetic (PK) parameter maps and uncertainty estimation from DCE-MRI. Methods In this single-center study, patients with adult-type diffuse gliom…
View article: Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement
Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement Open
While pruning methods effectively maintain model performance without extra training costs, they often focus solely on preserving crucial connections, overlooking the impact of pruned weights on subsequent fine-tuning or distillation, leadi…
View article: Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation
Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation Open
We propose Foreground-Covering Prototype Generation and Matching to resolve Few-Shot Segmentation (FSS), which aims to segment target regions in unlabeled query images based on labeled support images. Unlike previous research, which typica…
View article: Understanding Flatness in Generative Models: Its Role and Benefits
Understanding Flatness in Generative Models: Its Role and Benefits Open
Flat minima, known to enhance generalization and robustness in supervised learning, remain largely unexplored in generative models. In this work, we systematically investigate the role of loss surface flatness in generative models, both th…
View article: PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models
PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models Open
Despite recent advancements in federated learning (FL), the integration of generative models into FL has been limited due to challenges such as high communication costs and unstable training in heterogeneous data environments. To address t…
View article: Deep learning-based classification of diffusion-weighted imaging-fluid-attenuated inversion recovery mismatch
Deep learning-based classification of diffusion-weighted imaging-fluid-attenuated inversion recovery mismatch Open
The presence of a diffusion-weighted imaging (DWI)-fluid-attenuated inversion recovery (FLAIR) mismatch holds potential value in identifying candidates for recanalization treatment. However, the visual assessment of DWI-FLAIR mismatch is s…
View article: MultiDreamer3D: Multi-concept 3D Customization with Concept-Aware Diffusion Guidance
MultiDreamer3D: Multi-concept 3D Customization with Concept-Aware Diffusion Guidance Open
While single-concept customization has been studied in 3D, multi-concept customization remains largely unexplored. To address this, we propose MultiDreamer3D that can generate coherent multi-concept 3D content in a divide-and-conquer manne…
View article: BF-STVSR: B-Splines and Fourier-Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution
BF-STVSR: B-Splines and Fourier-Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution Open
While prior methods in Continuous Spatial-Temporal Video Super-Resolution (C-STVSR) employ Implicit Neural Representation (INR) for continuous encoding, they often struggle to capture the complexity of video data, relying on simple coordin…
View article: Dynamic-Aware Spatio-temporal Representation Learning for Dynamic MRI Reconstruction
Dynamic-Aware Spatio-temporal Representation Learning for Dynamic MRI Reconstruction Open
Dynamic MRI reconstruction, one of inverse problems, has seen a surge by the use of deep learning techniques. Especially, the practical difficulty of obtaining ground truth data has led to the emergence of unsupervised learning approaches.…
View article: Multimodal Semantic Segmentation in Yangtze River Economic Belt: Outcome of the 2024 IEEE WHISPERS MMSeg-YREB Challenge
Multimodal Semantic Segmentation in Yangtze River Economic Belt: Outcome of the 2024 IEEE WHISPERS MMSeg-YREB Challenge Open
With the growing availability of remote sensing (RS) data from diverse platforms, multimodal RS techniques have emerged as a transformative solution for large-scale semantic segmentation. In response, we developed MMSeg-YREB, a specialized…
View article: Snow-Calib: Deep Learning-Based Camera-LiDAR Extrinsic Calibration Under Snowy Weather Conditions
Snow-Calib: Deep Learning-Based Camera-LiDAR Extrinsic Calibration Under Snowy Weather Conditions Open
The fusion of camera and LiDAR sensors necessitates precise extrinsic calibration; however, existing deep learning methods are often computationally inefficient and perform poorly in dynamic and adverse environments, such as under snowfall…
View article: TransCalib: Automated Extrinsic Calibration of LiDAR–Camera Fusion Using Convolutional Transformer for Targetless Self-Alignment
TransCalib: Automated Extrinsic Calibration of LiDAR–Camera Fusion Using Convolutional Transformer for Targetless Self-Alignment Open
In autonomous systems and robotic applications, accurate extrinsic calibration between light detection and ranging (LiDAR) sensors and cameras is crucial for reliable sensor fusion. Several techniques have been developed, including target-…
View article: Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation
Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation Open
We propose Foreground-Covering Prototype Generation and Matching to resolve Few-Shot Segmentation (FSS), which aims to segment target regions in unlabeled query images based on labeled support images. Unlike previous research, which typica…
View article: LFCNet: Deep Learning-Based LiDAR-Fisheye Camera Online Automatic Targetless Extrinsic Calibration
LFCNet: Deep Learning-Based LiDAR-Fisheye Camera Online Automatic Targetless Extrinsic Calibration Open
This paper presents LFCNet, an end-to-end deep-learning framework for targetless extrinsic calibration between LiDAR and fisheye cameras. The method is specifically designed for autonomous driving systems, where accurate alignment of senso…
View article: Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement
Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement Open
While pruning methods effectively maintain model performance without extra training costs, they often focus solely on preserving crucial connections, overlooking the impact of pruned weights on subsequent fine-tuning or distillation, leadi…
View article: PosterLlama: Bridging Design Ability of Langauge Model to Contents-Aware Layout Generation
PosterLlama: Bridging Design Ability of Langauge Model to Contents-Aware Layout Generation Open
Visual layout plays a critical role in graphic design fields such as advertising, posters, and web UI design. The recent trend towards content-aware layout generation through generative models has shown promise, yet it often overlooks the …
View article: Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation
Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation Open
Generating high-quality videos that synthesize desired realistic content is a challenging task due to their intricate high-dimensionality and complexity of videos. Several recent diffusion-based methods have shown comparable performance by…
View article: STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models
STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models Open
Image generative models have made significant progress in generating realistic and diverse images, supported by comprehensive guidance from various evaluation metrics. However, current video generative models struggle to generate even shor…
View article: Enhancing Optical Camera Communication Performance for Collaborative Communication Using Positioning Information
Enhancing Optical Camera Communication Performance for Collaborative Communication Using Positioning Information Open
Optical camera communication (OCC) has emerged as a promising alternative technology for radio frequency (RF)-based communication systems. However, existing OCC approaches only consider transmitting data through broadcasting, without any a…
View article: Bridging the Domain Gap: A Simple Domain Matching Method for Reference-Based Image Super-Resolution in Remote Sensing
Bridging the Domain Gap: A Simple Domain Matching Method for Reference-Based Image Super-Resolution in Remote Sensing Open
Recently, reference-based image super-resolution (RefSR) has shown excellent\nperformance in image super-resolution (SR) tasks. The main idea of RefSR is to\nutilize additional information from the reference (Ref) image to recover the\nhig…
View article: Towards Robust Contrail Detection by Mitigating Label Bias via a Probabilistic Deep Learning Model: A Preliminary Study
Towards Robust Contrail Detection by Mitigating Label Bias via a Probabilistic Deep Learning Model: A Preliminary Study Open
Contrails, formed by jet flights, alter Earth's energy balance, prompting research into monitoring contrails and developing satellite-based automated contrail detection. This demand has advanced deep learning (DL)-based techniques. However…
View article: RADIO: Reference-Agnostic Dubbing Video Synthesis
RADIO: Reference-Agnostic Dubbing Video Synthesis Open
One of the most challenging problems in audio-driven talking head generation is achieving high-fidelity detail while ensuring precise synchronization. Given only a single reference image, extracting meaningful identity attributes becomes e…
View article: Efficient ϵ-Approximate k-Flexible Aggregate Nearest Neighbor Search for Arbitrary ϵ in Road Networks
Efficient ϵ-Approximate k-Flexible Aggregate Nearest Neighbor Search for Arbitrary ϵ in Road Networks Open
Recently, complicated spatial search algorithms have emerged as spatial-information-based applications, such as location-based services (LBS), and have become very diverse and frequent. The aggregate nearest neighbor (ANN) search is an ext…
View article: Can We Find Strong Lottery Tickets in Generative Models?
Can We Find Strong Lottery Tickets in Generative Models? Open
Yes. In this paper, we investigate strong lottery tickets in generative models, the subnetworks that achieve good generative performance without any weight update. Neural network pruning is considered the main cornerstone of model compress…
View article: TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models
TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models Open
We propose a robust and reliable evaluation metric for generative models by introducing topological and statistical treatments for rigorous support estimation. Existing metrics, such as Inception Score (IS), Frechet Inception Distance (FID…
View article: Efficient Storage of Fine-Tuned Models via Low-Rank Approximation of Weight Residuals
Efficient Storage of Fine-Tuned Models via Low-Rank Approximation of Weight Residuals Open
In this paper, we present an efficient method for storing fine-tuned models by leveraging the low-rank properties of weight residuals. Our key observation is that weight residuals in large overparameterized models exhibit even stronger low…
View article: Dynamic Fourier ptychography with deep spatiotemporal priors
Dynamic Fourier ptychography with deep spatiotemporal priors Open
Fourier ptychography (FP) involves the acquisition of several low-resolution intensity images of a sample under varying illumination angles. They are then combined into a high-resolution complex-valued image by solving a phase-retrieval pr…
View article: Fix the Noise: Disentangling Source Feature for Controllable Domain Translation
Fix the Noise: Disentangling Source Feature for Controllable Domain Translation Open
Recent studies show strong generative performance in domain translation especially by using transfer learning techniques on the unconditional generator. However, the control between different domain features using a single model is still c…