Publications (21)
Boosting Network Weight Separability via Feed-Backward Reconstruction
Jongmin Yu, Hyeontaek Oh
This paper proposes a new evaluation metric and boosting method for weight separability in neural network design. In contrast to general visual recognition methods designed to enco…
Context-Aware Multi-Task Learning for Traffic Scene Recognition in Autonomous Vehicles
Younkwan Lee, Jihyo Jeon, Jongmin Yu +1
Traffic scene recognition, which requires various visual classification tasks, is a critical ingredient in autonomous vehicles. However, most existing approaches treat each relevan…
An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination
Minkyung Kim, Jongmin Yu, Junsik Kim +2
Most deep anomaly detection models are based on learning normality from datasets due to the difficulty of defining abnormality by its diverse and inconsistent nature. Therefore, it…
Breaking Down Financial News Impact: A Novel AI Approach with Geometric Hypergraphs
Anoushka Harit, Zhongtian Sun, Jongmin Yu +1
In the fast-paced and volatile financial markets, accurately predicting stock movements based on financial news is critical for investors and analysts. Traditional models often str…
Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognition
Jongmin Yu, Yongsang Yoon, Moongu Jeon
In skeleton-based action recognition, graph convolutional networks (GCNs), which model human body skeletons using graphical components such as nodes and connections, have achieved…
Boosting Mapping Functionality of Neural Networks via Latent Feature Generation based on Reversible Learning
Jongmin Yu
This paper addresses a boosting method for mapping functionality of neural networks in visual recognition such as image classification and face recognition. We present reversible l…
Unsupervised Person Re-identification via Multi-Label Prediction and Classification based on Graph-Structural Insight
Jongmin Yu, Hyeontaek Oh
This paper addresses unsupervised person re-identification (Re-ID) using multi-label prediction and classification based on graph-structural insight. Our method extracts features f…
Camera-Tracklet-Aware Contrastive Learning for Unsupervised Vehicle Re-Identification
Jongmin Yu, Junsik Kim, Minkyung Kim +1
Recently, vehicle re-identification methods based on deep learning constitute remarkable achievement. However, this achievement requires large-scale and well-annotated datasets. In…
AlphaFace: High Fidelity and Real-time Face Swapper Robust to Facial Pose
Jongmin Yu, Hyeontaek Oh, Zhongtian Sun +3
Existing face-swapping methods often deliver competitive results in constrained settings but exhibit substantial quality degradation when handling extreme facial poses. To improve…
Adversarial Denoising Diffusion Model for Unsupervised Anomaly Detection
Jongmin Yu, Hyeontaek Oh, Jinhong Yang
In this paper, we propose the Adversarial Denoising Diffusion Model (ADDM). The ADDM is based on the Denoising Diffusion Probabilistic Model (DDPM) but complementarily trained by a…
Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamics
Minkyung Kim, Junsik Kim, Jongmin Yu +1
One-class classification has been a prevailing method in building deep anomaly detection models under the assumption that a dataset consisting of normal samples is available. In pr…
Multi-class Road Defect Detection and Segmentation using Spatial and Channel-wise Attention for Autonomous Road Repairing
Jongmin Yu, Chen Bene Chi, Sebastiano Fichera +3
Road pavement detection and segmentation are critical for developing autonomous road repair systems. However, developing an instance segmentation method that simultaneously perform…
Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination
Jongmin Yu, Hyeontaek Oh, Minkyung Kim +1
In this paper, we propose Normality-Calibrated Autoencoder (NCAE), which can boost anomaly detection performance on the contaminated datasets without any prior information or expli…
Quantifying Semantic Shift in Financial NLP: Robust Metrics for Market Prediction Stability
Zhongtian Sun, Chenghao Xiao, Anoushka Harit +1
Financial news is essential for accurate market prediction, but evolving narratives across macroeconomic regimes introduce semantic and causal drift that weaken model reliability.…
Unsupervised Vehicle Re-Identification via Self-supervised Metric Learning using Feature Dictionary
Jongmin Yu, Hyeontaek Oh
The key challenge of unsupervised vehicle re-identification (Re-ID) is learning discriminative features from unlabelled vehicle images. Numerous methods using domain adaptation hav…
Adversarially Domain-adaptive Latent Diffusion for Unsupervised Semantic Segmentation
Jongmin Yu, Zhongtian Sun, Chen Bene Chi +2
Semantic segmentation requires extensive pixel-level annotation, motivating unsupervised domain adaptation (UDA) to transfer knowledge from labelled source domains to unlabelled or…
Unsupervised Pixel-level Road Defect Detection via Adversarial Image-to-Frequency Transform
Jongmin Yu, Duyong Kim, Younkwan Lee +1
In the past few years, the performance of road defect detection has been remarkably improved thanks to advancements on various studies on computer vision and deep learning. Althoug…
Drivers Drowsiness Detection using Condition-Adaptive Representation Learning Framework
Jongmin Yu, Sangwoo Park, Sangwook Lee +1
We propose a condition-adaptive representation learning framework for the driver drowsiness detection based on 3D-deep convolutional neural network. The proposed framework consists…
Road Surface Defect Detection -- From Image-based to Non-image-based: A Survey
Jongmin Yu, Jiaqi Jiang, Sebastiano Fichera +4
Ensuring traffic safety is crucial, which necessitates the detection and prevention of road surface defects. As a result, there has been a growing interest in the literature on the…
From News to Returns: A Granger-Causal Hypergraph Transformer on the Sphere
Anoushka Harit, Zhongtian Sun, Jongmin Yu
We propose the Causal Sphere Hypergraph Transformer (CSHT), a novel architecture for interpretable financial time-series forecasting that unifies \emph{Granger-causal hypergraph st…
Active anomaly detection based on deep one-class classification
Minkyung Kim, Junsik Kim, Jongmin Yu +1
Active learning has been utilized as an efficient tool in building anomaly detection models by leveraging expert feedback. In an active learning framework, a model queries samples…