Author name cluster

Jee-Hyong Lee

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

EAAI Journal 2026 Journal Article

Adaptive spatial–temporal graph attention network for real-time traffic forecasting

Hao Huang
Jee-Hyong Lee
Yanling Ge
Seok-Beom Roh
Xue Zhao

Accurate and efficient Multivariate Time Series Forecasting (MTSF) plays a critical role in intelligent transportation systems by supporting real-time traffic management. However, achieving reliable forecasting remains challenging due to complex and dynamically evolving spatial–temporal patterns. Existing forecasting methods often fail to adapt effectively to these dynamic traffic conditions and typically incur high computational costs, significantly limiting their deployment in real-time traffic management scenarios. To address these engineering challenges, this study proposes a novel Attention-based Spatial-Temporal Network (ASTNet), explicitly designed for adaptive and efficient real-time traffic forecasting. ASTNet introduces two innovative Artificial Intelligence (AI)-driven modules: an Adaptive Spatial Graph Encoder (ASGE), which dynamically models evolving spatial dependencies from real-time traffic data, thus overcoming the limitations of static graph structures; and a Temporal Attention-Gated Unit (TAGU), which efficiently captures critical temporal dependencies through the integration of recurrent gating mechanisms and self-attention techniques. Extensive evaluations conducted on widely-used traffic benchmark datasets (PEMS04, METR-LA, etc.) confirm that ASTNet achieves superior predictive accuracy and robustness compared to state-of-the-art methods, while significantly reducing inference latency. Ablation studies further validate that the combined innovations of ASGE and TAGU are crucial for ASTNet’s outstanding performance, highlighting its practical suitability and strong potential for deployment in real-time intelligent transportation applications.

Details DOI

AAAI Conference 2026 Conference Paper

BD-Net: Has Depth-Wise Convolution Ever Been Applied in Binary Neural Networks?

Doyoung Kim
Jin-Seop Lee
Noo-ri Kim
SungJoon Lee
Jee-Hyong Lee

Recent advances in model compression have highlighted the potential of low-bit precision techniques, with Binary Neural Networks (BNNs) attracting attention for their extreme efficiency. However, extreme quantization in BNNs limits representational capacity and destabilizes training, posing significant challenges for lightweight architectures with depth-wise convolutions. To address this, we propose a 1.58-bit convolution to enhance expressiveness and a pre-BN residual connection to stabilize optimization by improving the Hessian condition number. These innovations enable, to the best of our knowledge, the first successful binarization of depth-wise convolutions in BNNs. Our method achieves 33M OPs on ImageNet with MobileNet V1, establishing a new state-of-the-art in BNNs by outperforming prior methods with comparable OPs. Moreover, it consistently outperforms existing methods across various datasets, including CIFAR-10, CIFAR-100, STL-10, Tiny ImageNet, and Oxford Flowers 102, with accuracy improvements of up to 9.3 percentage points.

PDF Details DOI

AAAI Conference 2025 Conference Paper

DomCLP: Domain-wise Contrastive Learning with Prototype Mixup for Unsupervised Domain Generalization

Jin-Seop Lee
Noo-ri Kim
Jee-Hyong Lee

Self-supervised learning (SSL) methods based on the instance discrimination tasks with InfoNCE have achieved remarkable success. Despite their success, SSL models often struggle to generate effective representations for unseen-domain data. To address this issue, research on unsupervised domain generalization (UDG), which aims to develop SSL models that can generate domain-irrelevant features, has been conducted. Most UDG approaches utilize contrastive learning with InfoNCE to generate representations, and perform feature alignment based on strong assumptions to generalize domain-irrelevant common features from multi-source domains. However, existing methods that rely on instance discrimination tasks are not effective at extracting domain-irrelevant common features. This leads to the suppression of domain-irrelevant common features and the amplification of domain-relevant features, thereby hindering domain generalization. Furthermore, strong assumptions underlying feature alignment can lead to biased feature learning, reducing the diversity of common features. In this paper, we propose a novel approach, DomCLP, Domain-wise Contrastive Learning with Prototype Mixup. We explore how InfoNCE suppresses domain-irrelevant common features and amplifies domain-relevant features. Based on this analysis, we propose Domain-wise Contrastive Learning (DCon) to enhance domain-irrelevant common features. We also propose Prototype Mixup Learning (PMix) to generalize domain-irrelevant common features across multiple domains without relying on strong assumptions. The proposed method consistently outperforms state-of-the-art methods on the PACS and DomainNet datasets across various label fractions, showing significant improvements.

PDF Details DOI

EAAI Journal 2024 Journal Article

Automation of trimming die design inspection by zigzag process between AI and CAD domains

Jin-Seop Lee
Tae-Hyun Kim
Sang-Hwan Jeon
Sung-Hyun Park
Sang-Hi Kim
Eun-Ho Lee
Jee-Hyong Lee

Quality control using artificial intelligence (AI) has led to considerable improvements in the manufacturing industry. However, inspection of computer-aided design (CAD) drawing to prevent potential errors is still performed manually by engineers. The design inspection which involves sequential and repetitive processes is labor-intensive, time-consuming, and prone to human error. In this study, we developed an automatic design inspection system for CAD data by integrating AI module and CAD software. The target product of this study is automobile trimming die design. The AI modules replace the engineers’ judgment, and the CAD software performs the operations requested by the AI modules. The design inspection is completed through a zigzag interaction between the AI modules and CAD software by a one-click operation without the intervention of experts. In the zigzag interaction process, 3D CAD files are converted to 2D images for interaction from the CAD software to the AI modules, and the output of the AI modules is transferred to the CAD software through VBA macros. The AI modules are designed to be CAD-independent and data-efficient; therefore, they can be easily adapted to other CAD software and achieve a high performance, even when trained with a few trimming dies. The length measurement error is only 2. 4 % on average, which is at the 14th place out of 18 grades according to ISO 286–1: 1988 standard tolerance. Additionally, the inspection time is reduced to approximately one-fifth of the manual inspection time by experts.

Details DOI