https://github.com/yeonghyeon/yeonghyeon
https://github.com/yeonghyeon/yeonghyeon
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/yeonghyeon/yeonghyeon
- Owner: YeongHyeon
- Created: 2020-10-12T04:48:20.000Z (almost 5 years ago)
- Default Branch: main
- Last Pushed: 2025-06-17T15:32:56.000Z (4 months ago)
- Last Synced: 2025-06-17T16:41:45.365Z (4 months ago)
- Size: 1.63 MB
- Stars: 6
- Watchers: 1
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
Recent Publications
#### International Journal
+ Visual Defect Obfuscation Based Self-Supervised Anomaly Detection
YeongHyeon Park, Sungho Kang, Myung Jin Kim, Yeonho Lee, Hyeong Seok Kim, Juneho Yi
*Scientific Reports*, 2024
[[paper]](https://www.nature.com/articles/s41598-024-69698-5) [[poster]](https://yeonghyeon.github.io/pdfs/SciRep2024_Park-EAR.pdf)
+ Boost-up Efficiency of Defective Solar Panel Detection with Pre-trained Attention Recycling
YeongHyeon Park, Myung Jin Kim, Uju Gim, Juneho Yi
*IEEE Transactions on Industry Applications*, 2023
[[paper]](https://ieeexplore.ieee.org/document/10065567) [[slide]](https://yeonghyeon.github.io/pdfs/TIA2023_Park-Solar.pdf)
#### International Conference
+ Feature Attenuation of Defective Representation Can Resolve Incomplete Masking on Anomaly Detection
YeongHyeon Park, Sungho Kang, Myung Jin Kim, Hyeong Seok Kim, Juneho Yi
*IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPR 2025 VAND3.0 workshop)*
[[paper]](https://openaccess.thecvf.com/content/CVPR2025W/VAND/html/Park_Feature_Attenuation_of_Defective_Representation_Can_Resolve_Incomplete_Masking_on_CVPRW_2025_paper.html) [[poster]](https://yeonghyeon.github.io/pdfs/CVPRW2025_Park-FADeR.pdf)
+ Contrastive Language Prompting to Ease False Positives in Medical Anomaly Detection
YeongHyeon Park, Myung Jin Kim, Hyeong Seok Kim
*IEEE International Symposium on Biomedical Imaging (ISBI 2025)*
[[paper]](https://arxiv.org/abs/2411.07546) [[poster]](https://yeonghyeon.github.io/pdfs/ISBI2025_Park-CLAP.pdf)
+ Neural Network Training Strategy to Enhance Anomaly Detection Performance: A Perspective on Reconstruction Loss Amplification
YeongHyeon Park, Sungho Kang, Myung Jin Kim, Hyeonho Jeong, Hyunkyu Park, Hyeong Seok Kim, Juneho Yi
*IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)*
[[paper]](https://arxiv.org/abs/2308.14595) [[poster]](https://yeonghyeon.github.io/pdfs/ICASSP2024_Park-LAMP.pdf)
Repositories
```
Repositories
│
├── TensorFlow
│ ├── Publications (Sorted by year in ascending order)
│ │ ├── Preprocessing Method for Performance Enhancement in CNN-based STEMI Detection from 12-lead ECG
│ │ │ ├── IEEE Access (2019): https://ieeexplore.ieee.org/abstract/document/8771175
│ │ │ └── Source: https://github.com/YeongHyeon/Preprocessing-Method-for-STEMI-Detection
│ │ ├── Arrhythmia detection in electrocardiogram based on recurrent neural network encoder–decoder with Lyapunov exponent
│ │ │ ├── IEEJ (2018): https://onlinelibrary.wiley.com/doi/abs/10.1002/tee.22927
│ │ │ └── Source: https://github.com/YeongHyeon/Arrhythmia_Detection_RNN_and_Lyapunov
│ │ └── Fast Adaptive RNN Encoder–Decoder for Anomaly Detection in SMD Assembly Machine
│ │ ├── MDPI (2018): https://www.mdpi.com/1424-8220/18/10/3573
│ │ └── Source: https://github.com/YeongHyeon/FARED_for_Anomaly_Detection
│ │
│ ├── Discriminative Model
│ │ ├── Series Inception
│ │ │ ├── Inception: https://github.com/YeongHyeon/Inception_Simplified-TF2
│ │ │ └── XCeption: https://github.com/YeongHyeon/XCeption-TF2
│ │ ├── Series Residual
│ │ │ ├── ResNet: https://github.com/YeongHyeon/ResNet-TF2
│ │ │ ├── ResNeXt: https://github.com/YeongHyeon/ResNeXt-TF2
│ │ │ ├── WRN: https://github.com/YeongHyeon/WideResNet_WRN-TF2
│ │ │ ├── ResNeSt: https://github.com/YeongHyeon/ResNeSt-TF2
│ │ │ └── ReXNet: https://github.com/YeongHyeon/ReXNet-TF2
│ │ ├── Series Bayesian / Gaussian
│ │ │ └── SWA-Gaussian: https://github.com/YeongHyeon/SWA-Gaussian-TF2
│ │ ├── Series Graph
│ │ │ └── PIPGCN: https://github.com/YeongHyeon/PIPGCN-TF2
│ │ └── Ohters
│ │ ├── SE-Net: https://github.com/YeongHyeon/SENet-Simple
│ │ ├── SK-Net: https://github.com/YeongHyeon/SKNet-TF2
│ │ ├── GhostNet: https://github.com/YeongHyeon/GhostNet
│ │ ├── Network-in-Network: https://github.com/YeongHyeon/Network-in-Network-TF2
│ │ ├── Shake-Shake Regularization: https://github.com/YeongHyeon/Shake-Shake
│ │ ├── MNIST Attention Map: https://github.com/YeongHyeon/MNIST_AttentionMap
│ │ └── MLP-Mixer: https://github.com/YeongHyeon/MLP-Mixer-TF2
│ │
│ ├── Generative Model
│ │ ├── Generals
│ │ │ ├── GAN: https://github.com/YeongHyeon/GAN-TF
│ │ │ ├── WGAN: https://github.com/YeongHyeon/WGAN-TF
│ │ │ ├── CGAN: https://github.com/YeongHyeon/CGAN-TF
│ │ │ ├── Normalizing Flow: https://github.com/YeongHyeon/Normalizing-Flow-TF2
│ │ │ └── Transformer: https://github.com/YeongHyeon/Transformer-TF2
│ │ ├── Anomaly Detection
│ │ │ ├── CVAE (Convolution & Variational): https://github.com/YeongHyeon/CVAE-AnomalyDetection
│ │ │ ├── GANomaly: https://github.com/YeongHyeon/GANomaly-TF
│ │ │ ├── Skip-GANomaly: https://github.com/YeongHyeon/Skip-GANomaly
│ │ │ ├── ConAD: https://github.com/YeongHyeon/ConAD
│ │ │ ├── MemAE: https://github.com/YeongHyeon/MemAE
│ │ │ ├── f-AnoGAN: https://github.com/YeongHyeon/f-AnoGAN-TF
│ │ │ ├── DGM: https://github.com/YeongHyeon/DGM-TF
│ │ │ └── ADAE: https://github.com/YeongHyeon/ADAE-TF
│ │ └── Special Purpose
│ │ ├── SRCNN: https://github.com/YeongHyeon/Super-Resolution_CNN
│ │ ├── Context-Encoder: https://github.com/YeongHyeon/Context-Encoder
│ │ └── Sequence-Autoencoder: https://github.com/YeongHyeon/Sequence-Autoencoder
│ │
│ └── Additional Methods
│ ├── SGDR: https://github.com/YeongHyeon/ResNet-with-SGDR-TF2
│ ├── Learning rate WarmUp: https://github.com/YeongHyeon/ResNet-with-LRWarmUp-TF2
│ └── ArcFace: https://github.com/YeongHyeon/ArcFace-TF2
│
└── PyTorch
├── Discriminative Model
│ └── Ohters
│ ├── MLP-Mixer: https://github.com/YeongHyeon/MLP-Mixer-PyTorch
│ ├── GhostNet: https://github.com/YeongHyeon/GhostNet-PyTorch
│ └── DINO: https://github.com/YeongHyeon/DINO_MNIST-PyTorch
└── Generative Model
├── Anomaly Detection
│ ├── CVAE (Convolution & Variational): https://github.com/YeongHyeon/CVAE-AnomalyDetection-PyTorch
│ ├── GANomaly: https://github.com/YeongHyeon/GANomaly-PyTorch
│ ├── ConAD: https://github.com/YeongHyeon/ConAD-PyTorch
│ └── RIAD: https://github.com/YeongHyeon/RIAD-PyTorch
└── Special Purpose
└── SRCNN: https://github.com/YeongHyeon/Super-Resolution_CNN-PyTorch
```
Kaggle
#### Notebooks Expert :mortar_board:
* :3rd_place_medal: RSNA23 EASY DICOM Confirmation & Volume Generation @ RSNA 2023 Abdominal Trauma Detection
* :3rd_place_medal: Riiid! step by step guide for Beginner/EDA/PyTorch @ Riiid Answer Correctness Prediction
* :3rd_place_medal: Easy to run, Keras Full Package! (including EDA) @ [T-Academy X KaKr] 성인 인구조사 소득 예측 대회
* :3rd_place_medal: Shopee, Easy to Run! @ Shopee - Price Match Guarantee
* :3rd_place_medal: SETI, step by step guide for Beginner/EDA/TF @ SETI Breakthrough Listen - E.T. Signal Search
* :3rd_place_medal: Convert DICOM to Numpy Array (Super Simple) @ RSNA-MICCAI Brain Tumor Radiogenomic Classification
* :3rd_place_medal: Baseline UAD (w/ Fashion MNIST dataset)
* :satisfied: Step-by-Step MNIST | Full Package, EDA, TensorFlow @ Digit Recognizer
* :satisfied: Step-by-Step, Herbarium 2021! @ Herbarium 2021 - Half-Earth Challenge - FGVC8
#### Competition
* :3rd_place_medal: RSNA 2023 Abdominal Trauma Detection
#### Datasets
* :satisfied: RSNA-MICCAI BTRC2021 @ RSNA-MICCAI Brain Tumor Radiogenomic Classification