no code implementations • 21 Feb 2024 • Mingyu Guan, Jack W. Stokes, Qinlong Luo, Fuchen Liu, Purvanshi Mehta, Elnaz Nouri, Taesoo Kim
In this paper, we present HetTree, a novel heterogeneous tree graph neural network that models both the graph structure and heterogeneous aspects in a scalable and effective manner.
no code implementations • 31 Dec 2023 • Hyeonjae Jeon, Junghyun Seo, Taesoo Kim, Sungho Son, Jungki Lee, Gyeungho Choi, Yongseob Lim
Finally, we discuss the limitation and the future directions of the deep neural network-based perception algorithms and autonomous driving dataset generation based on image-to-image translation.
no code implementations • 18 Jul 2023 • Sangdon Park, Taesoo Kim
Uncertainty learning and quantification of models are crucial tasks to enhance the trustworthiness of the models.
no code implementations • 20 Jun 2023 • Daniel Rho, Taesoo Kim, Sooill Park, JaeHyun Park, JaeHan Park
In this work, we propose a new perspective to understand the role of margins based on gradient analysis.
no code implementations • 28 Mar 2023 • Hyeonsoo Lee, Junha Kim, Eunkyung Park, Minjeong Kim, Taesoo Kim, Thijs Kooi
Recently, deep learning models have shown the potential to predict breast cancer risk and enable targeted screening strategies, but current models do not consider the change in the breast over time.
1 code implementation • 17 Nov 2022 • Sangdon Park, Osbert Bastani, Taesoo Kim
To address the oracle problem, we propose an adaptive conformal consensus (ACon$^2$) algorithm that derives a consensus set of data from multiple oracle contracts via the recent advance in online uncertainty quantification learning.
no code implementations • 31 Oct 2022 • Sangdon Park, Xiang Cheng, Taesoo Kim
Memory-safety bugs introduce critical software-security issues.
no code implementations • 13 Oct 2022 • Gunhee Nam, Taesoo Kim, Sanghyup Lee, Thijs Kooi
We validate our approach using a large scale proprietary dataset of over 100K radiographs as well as publicly available RANZCR-CLiP Kaggle Challenge dataset and show that our method consistently outperforms commonly used regression-based detection models as well as commonly used pixel-wise classification methods.
no code implementations • ICASSP 2022 • Taesoo Kim, Jiho Chang, Jong Hwan Ko
In this paper, we propose adversarial domain adaptive VAD (ADA-VAD), which is a deep neural network (DNN) based VAD method highly robust to audio samples with various noise types and low SNRs.
Ranked #4 on Activity Detection on AVA-Speech (ROC-AUC metric)
no code implementations • 10 Jun 2021 • Hyungjoon Koo, Soyeon Park, Daejin Choi, Taesoo Kim
Recently, binary analysis techniques based on machine learning have been proposed to automatically reconstruct the code representation of a binary instead of manually crafting specifics of the analysis algorithm.
2 code implementations • 23 Sep 2019 • Se Kwon Lee, Jayashree Mohan, Sanidhya Kashyap, Taesoo Kim, Vijay Chidambaram
We present Recipe, a principled approach for converting concurrent DRAM indexes into crash-consistent indexes for persistent memory (PM).
Distributed, Parallel, and Cluster Computing Databases Data Structures and Algorithms