Kwanseok Oh's Projects
This repository contains the 3D shapes dataset, used in Kim, Hyunjik and Mnih, Andriy. "Disentangling by Factorising." In Proceedings of the 35th International Conference on Machine Learning (ICML). 2018. to assess the disentanglement properties of unsupervised learning methods.
Tensorflow implementation of "Born Identity Network: Multi-way Counterfactual Map Generation to Explain a Classifier's Decision"
Mini-project using the TensorFlow and PyTorch framework jointly
Mini-project using the PyTorch framework
Pytorch implementation of "FIESTA: Fourier-based Semantic Augmentation with Uncertainty Guidance for Enhanced Domain Generalizability in Medical Image Segmentation" [Submitted to MedIA]
Pytorch implementation of "Age-Aware Guidance via Masking-Based Attention in Face Aging" [CIKM 2023]
A toolbox to iNNvestigate neural networks' predictions!
Book about interpretable machine learning
Tensorflow implementation of "Learn-Explain-Reinforce: Counterfactual Reasoning and Its Guidance to Reinforce an Alzheimer's Disease Diagnosis Model" [TPAMI 2022]
Tensorflow implementation of "A Quantitatively Interpretable Model for Alzheimer’s Disease Prediction Using Deep Counterfactuals" [MedNeurIPS2022], [Submitted to TPAMI]
Pytorch re-implementation of MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis.
XAI approaches based on the TensorFlow framework to understand neural networks decision
An open access book on scientific visualization using python and matplotlib
Codes and models for Medical Image Analysis (MIA) 2023 paper. Segment Anything Model for Medical Images?.
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
[AAAI 2023] Official PyTorch implementation of the paper "SLAug: Rethinking Data Augmentation for Single-source Domain Generalization in Medical Image Segmentation"
Tensorflow implementation of Swin Transformer model.
PyTorch implementation of "Transferring Ultra-high Field Representations for Intensity-Guided Brain Segmentation of Low Field MRI" [MICCAI 2022], [Submitted to MedIA]
A source code for "VIGNet: A deep convolutional neural network for EEG-based driver vigilance estiamtion"
Interesting resources related to XAI (Explainable Artificial Intelligence)