Search Results for author: Daehyun Kim

Found 10 papers, 2 papers with code

ScieNet: Deep Learning with Spike-assisted Contextual Information Extraction

no code implementations11 Sep 2019 Xueyuan She, Yun Long, Daehyun Kim, Saibal Mukhopadhyay

ScieNet integrates unsupervised learning using spiking neural network (SNN) for unsupervised contextual informationextraction with a back-end DNN trained for classification.

Autonomous Vehicles Classification +2

SAFE-DNN: A Deep Neural Network with Spike Assisted Feature Extraction for Noise Robust Inference

no code implementations25 Sep 2019 Xueyuan She, Priyabrata Saha, Daehyun Kim, Yun Long, Saibal Mukhopadhyay

We present a Deep Neural Network with Spike Assisted Feature Extraction (SAFE-DNN) to improve robustness of classification under stochastic perturbation of inputs.

Classification

Local Connectivity-Based Density Estimation for Face Clustering

1 code implementation CVPR 2023 Junho Shin, Hyo-Jun Lee, Hyunseop Kim, Jong-Hyeon Baek, Daehyun Kim, Yeong Jun Koh

For this purpose, we propose a reliable density estimation algorithm based on local connectivity between K nearest neighbors (KNN).

Clustering Connectivity Estimation +2

Luminance-aware Color Transform for Multiple Exposure Correction

1 code implementation ICCV 2023 Jong-Hyeon Baek, Daehyun Kim, Su-Min Choi, Hyo-Jun Lee, HanUl Kim, Yeong Jun Koh

Images captured with irregular exposures inevitably present unsatisfactory visual effects, such as distorted hue and color tone.

Characterizing the Feasible Payoff Set of OLG Repeated Games

no code implementations23 Mar 2023 Daehyun Kim, Chihiro Morooka

We study the set of feasible payoffs of OLG repeated games with general stage games.

On the Value of Information Structures in Stochastic Games

no code implementations17 Aug 2023 Daehyun Kim, Ichiro Obara

Our main result is the monotonicity of the limit perfect public equilibrium (PPE) payoff set with respect to this information order: we show that the limit PPE payoff sets with one information structure is larger than the limit PPE payoff sets with another information structure state by state if the latter information structure is a weighted garbling of the former.

Deep Neural Network Models Trained With A Fixed Random Classifier Transfer Better Across Domains

no code implementations28 Feb 2024 Hafiz Tiomoko Ali, Umberto Michieli, Ji Joong Moon, Daehyun Kim, Mete Ozay

Inspired by NC properties, we explore in this paper the transferability of DNN models trained with their last layer weight fixed according to ETF.

Fine-Grained Image Classification Transfer Learning

FFT-based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images

no code implementations21 Mar 2024 Elena Camuffo, Umberto Michieli, Jijoong Moon, Daehyun Kim, Mete Ozay

Improving model robustness in case of corrupted images is among the key challenges to enable robust vision systems on smart devices, such as robotic agents.

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