44 citations · 96 across the 8 of their papers we have counts for
10 papers
Closing the Gap Between Synthetic and Ground Truth Time Series Distributions via Neural Mapping
Daesoo Lee, Sara Malacarne, Erlend Aune
In this paper, we introduce Neural Mapper for Vector Quantized Time Series Generator (NM-VQTSG), a novel method aimed at addressing fidelity challenges in vector quantized (VQ) tim…
Blending Low and High-Level Semantics of Time Series for Better Masked Time Series Generation
Johan Vik Mathisen, Erlend Lokna, Daesoo Lee +1
State-of-the-art approaches in time series generation (TSG), such as TimeVQVAE, utilize vector quantization-based tokenization to effectively model complex distributions of time se…
Explainable Time Series Anomaly Detection using Masked Latent Generative Modeling
Daesoo Lee, Sara Malacarne, Erlend Aune
We present a novel time series anomaly detection method that achieves excellent detection accuracy while offering a superior level of explainability. Our proposed method, TimeVQVAE…
Latent Diffusion Model for Conditional Reservoir Facies Generation
Daesoo Lee, Oscar Ovanger, Jo Eidsvik +3
Creating accurate and geologically realistic reservoir facies based on limited measurements is crucial for field development and reservoir management, especially in the oil and gas…
Masked Generative Modeling with Enhanced Sampling Scheme
Daesoo Lee, Erlend Aune, Sara Malacarne
This paper presents a novel sampling scheme for masked non-autoregressive generative modeling. We identify the limitations of TimeVQVAE, MaskGIT, and Token-Critic in their sampling…
Vector Quantized Time Series Generation with a Bidirectional Prior Model
Daesoo Lee, Sara Malacarne, Erlend Aune
Time series generation (TSG) studies have mainly focused on the use of Generative Adversarial Networks (GANs) combined with recurrent neural network (RNN) variants. However, the fu…
Better Reasoning Behind Classification Predictions with BERT for Fake News Detection
Daesoo Lee
Fake news detection has become a major task to solve as there has been an increasing number of fake news on the internet in recent years. Although many classification models have b…
VNIbCReg: VICReg with Neighboring-Invariance and better-Covariance Evaluated on Non-stationary Seismic Signal Time Series
Daesoo Lee, Erlend Aune, Nadège Langet +1
One of the latest self-supervised learning (SSL) methods, VICReg, showed a great performance both in the linear evaluation and the fine-tuning evaluation. However, VICReg is propos…
Reinforcement Learning-Based Automatic Berthing System
Daesoo Lee
Previous studies on automatic berthing systems based on artificial neural network (ANN) showed great berthing performance by training the ANN with ship berthing data as training da…
Computer Vision Self-supervised Learning Methods on Time Series
Daesoo Lee, Erlend Aune
Self-supervised learning (SSL) has had great success in both computer vision. Most of the current mainstream computer vision SSL frameworks are based on Siamese network architectur…