Search Results for author: Seo Taek Kong

Found 6 papers, 1 papers with code

Key Feature Replacement of In-Distribution Samples for Out-of-Distribution Detection

1 code implementation26 Dec 2022 Jaeyoung Kim, Seo Taek Kong, Dongbin Na, Kyu-Hwan Jung

We first deduce that OOD images are perceived by a deep neural network to be semantically similar to in-distribution samples when they share a common background, as deep networks are observed to incorrectly classify such images with high confidence.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Almost Boltzmann Exploration

no code implementations25 Jan 2019 Harsh Gupta, Seo Taek Kong, R. Srikant, Weina Wang

In this paper, we show that a simple modification to Boltzmann exploration, motivated by a variation of the standard doubling trick, achieves $O(K\log^{1+\alpha} T)$ regret for a stochastic MAB problem with $K$ arms, where $\alpha>0$ is a parameter of the algorithm.

Multi-Armed Bandits

Better Optimization can Reduce Sample Complexity: Active Semi-Supervised Learning via Convergence Rate Control

no code implementations1 Jan 2021 Seo Taek Kong, Soomin Jeon, Jaewon Lee, Hong-Seok Lee, Kyu-Hwan Jung

We name this AL scheme convergence rate control (CRC), and our experiments show that a deep neural network trained using a combination of CRC and a recently proposed SSL algorithm can quickly achieve high performance using far less labeled samples than SL.

Active Learning

A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexity

no code implementations8 Apr 2021 Seo Taek Kong, Soomin Jeon, Dongbin Na, Jaewon Lee, Hong-Seok Lee, Kyu-Hwan Jung

Although unlabeled data is readily available in pool-based AL, AL algorithms are usually evaluated by measuring the increase in supervised learning (SL) performance at consecutive acquisition steps.

Active Learning

A Provably Improved Algorithm for Crowdsourcing with Hard and Easy Tasks

no code implementations14 Feb 2023 Seo Taek Kong, Saptarshi Mandal, Dimitrios Katselis, R. Srikant

After separating tasks by type, any Dawid-Skene algorithm (i. e., any algorithm designed for the Dawid-Skene model) can be applied independently to each type to infer the truth values.

Vocal Bursts Type Prediction

Self-accumulative Vision Transformer for Bone Age Assessment Using the Sauvegrain Method

no code implementations29 Mar 2023 Hong-Jun Choi, Dongbin Na, Kyungjin Cho, Byunguk Bae, Seo Taek Kong, Hyunjoon An

This study presents a novel approach to bone age assessment (BAA) using a multi-view, multi-task classification model based on the Sauvegrain method.

Cannot find the paper you are looking for? You can Submit a new open access paper.