Seungjae Shin

I am a Ph.D. student at  Applied Artificial Intelligence Lab, advised by Prof. Il-Chul Moon at Korea Advanced Institute of Science and Technology (KAIST). Previously, I received B.S in Industrial Engineering from KAIST in Feb. 2018 and M.S in industrial Engineering from KAIST in Feb. 2020, respectively. 


tmdwo0910 [at] kaist [dot] ac [dot] kr // tmdwo0910 [at] gmail [dot] com 

Google Scholar / LinkedIn / Twitter / CV


My research has been focused on (but not limited to)

Publications (C: Conferences, J: Journal, W: Workshop, P: preprint, * denotes the equal contribution. )

1st (or Co-1st) Authored 

[C12] Unknown Domain Inconsistency Minimization for Domain Generalization [TBD]


[C9] Frequency domain-based Dataset Distillation [paper, arxiv, code]


[C8] Loss Curvature Matching for Dataset Selection and Condensation [paper, arxiv, code]


[W2] Improving Group-based Robustness and Calibration via Ordered Risk and Confidence Regularization [paper]


[C7] From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model [arxiv, paper, code]


[J2] Evaluation of optimal scene time interval for out-of-hospital cardiac arrest using a deep neural network [paper]


[C2] Neutralizing Gender Bias in Word Embedding with Latent Disentanglement and Counterfactual Generation [paper]


Co-Authored 

[C11] Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning [TBD]


[C10] Make Prompts Adaptable : Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior [TBD]


[C6] Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation [arxiv, paper, code]


[C5] ABC : Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning [paper, code]


[C4] Refine Myself by Teaching Myself : Feature Refinement via Self-Knowledge Distillation [paper, code]


[C3] Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder [paper]


[C1] Bivariate Beta-LSTM [paper, code]


[W1] FEWER : Federated Weight Recovery [paper]


[J1] Forecasting the Concentration of Particulate Matter in the Seoul Metropolitan Area Using a Gaussian Process Model  [paper]


[P3] Posterior-Aided Regularization for Likelihood-Free Inference  [pdf]


[P2] Adversarial Likelihood-Free Inference on Black-Box Generator [pdf]


[P1] Generalized Gumbel-Softmax Gradient Estimator for Various Discrete Random Variables [pdf]



Education


Experience


Honors & Awards


Academic Services


Program Committee (Conference Reviewer)

Other Interests