Search Results for author: Dohyung Kim

Found 16 papers, 6 papers with code

Can LLMs Recognize Toxicity? Structured Toxicity Investigation Framework and Semantic-Based Metric

no code implementations10 Feb 2024 Hyukhun Koh, Dohyung Kim, Minwoo Lee, Kyomin Jung

In the pursuit of developing Large Language Models (LLMs) that adhere to societal standards, it is imperative to discern the existence of toxicity in the generated text.

Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identification

no code implementations ICCV 2023 Geon Lee, SangHoon Lee, Dohyung Kim, Younghoon Shin, Yongsang Yoon, Bumsub Ham

To address the camera bias problem, we also introduce a camera-diversity (CD) loss encouraging person images of the same pseudo label, but captured across various cameras, to involve more for discriminative feature learning, providing person representations robust to inter-camera variations.

Domain Adaptation Domain Adaptive Person Re-Identification +4

Fair Contrastive Learning for Facial Attribute Classification

1 code implementation CVPR 2022 Sungho Park, Jewook Lee, Pilhyeon Lee, Sunhee Hwang, Dohyung Kim, Hyeran Byun

Through extensive experiments on CelebA and UTK Face, we validate that the proposed method significantly outperforms SupCon and existing state-of-the-art methods in terms of the trade-off between top-1 accuracy and fairness.

Attribute Classification +6

Distance-aware Quantization

no code implementations ICCV 2021 Dohyung Kim, Junghyup Lee, Bumsub Ham

This alleviates the gradient mismatch, but causes a quantizer gap problem.

Quantization

Decoding the shift-invariant data: applications for band-excitation scanning probe microscopy

1 code implementation20 Apr 2021 Yongtao Liu, Rama K. Vasudevan, Kyle Kelley, Dohyung Kim, Yogesh Sharma, Mahshid Ahmadi, Sergei V. Kalinin, Maxim Ziatdinov

A shift-invariant variational autoencoder (shift-VAE) is developed as an unsupervised method for the analysis of spectral data in the presence of shifts along the parameter axis, disentangling the physically-relevant shifts from other latent variables.

Denoising Dimensionality Reduction

Network Quantization with Element-wise Gradient Scaling

1 code implementation CVPR 2021 Junghyup Lee, Dohyung Kim, Bumsub Ham

Network quantization aims at reducing bit-widths of weights and/or activations, particularly important for implementing deep neural networks with limited hardware resources.

Image Classification Quantization

VOTE400(Voide Of The Elderly 400 Hours): A Speech Dataset to Study Voice Interface for Elderly-Care

no code implementations20 Jan 2021 Minsu Jang, Sangwon Seo, Dohyung Kim, Jaeyeon Lee, Jaehong Kim, Jun-Hwan Ahn

This paper introduces a large-scale Korean speech dataset, called VOTE400, that can be used for analyzing and recognizing voices of the elderly people.

speech-recognition Speech Recognition

FairFaceGAN: Fairness-aware Facial Image-to-Image Translation

no code implementations1 Dec 2020 Sunhee Hwang, Sungho Park, Dohyung Kim, Mirae Do, Hyeran Byun

Further, we also evaluate image translation performances, where FairFaceGAN shows competitive results, compared to those of existing methods.

Attribute Fairness +2

Learning with Privileged Information for Efficient Image Super-Resolution

no code implementations ECCV 2020 Wonkyung Lee, Junghyup Lee, Dohyung Kim, Bumsub Ham

The student and the decoder in the teacher, having the same network architecture as FSRCNN, try to reconstruct HR images.

Image Super-Resolution SSIM

README: REpresentation learning by fairness-Aware Disentangling MEthod

no code implementations7 Jul 2020 Sungho Park, Dohyung Kim, Sunhee Hwang, Hyeran Byun

After the representation learning, this disentangled representation is leveraged for fairer downstream classification by excluding the subspace with the protected attribute information.

Attribute Fairness +1

ETRI-Activity3D: A Large-Scale RGB-D Dataset for Robots to Recognize Daily Activities of the Elderly

1 code implementation4 Mar 2020 Jinhyeok Jang, Dohyung Kim, Cheonshu Park, Minsu Jang, Jaeyeon Lee, Jaehong Kim

To cope with this situation, we introduce a new dataset called ETRI-Activity3D, focusing on the daily activities of the elderly in robot-view.

Learning Semantic Correspondence Exploiting an Object-level Prior

no code implementations29 Nov 2019 Junghyup Lee, Dohyung Kim, Wonkyung Lee, Jean Ponce, Bumsub Ham

We address the problem of semantic correspondence, that is, establishing a dense flow field between images depicting different instances of the same object or scene category.

Object Semantic correspondence

Imaging Mechanism for Hyperspectral Scanning Probe Microscopy via Gaussian Process Modelling

2 code implementations26 Nov 2019 Maxim Ziatdinov, Dohyung Kim, Sabine Neumayer, Rama K. Vasudevan, Liam Collins, Stephen Jesse, Mahshid Ahmadi, Sergei V. Kalinin

We investigate the ability to reconstruct and derive spatial structure from sparsely sampled 3D piezoresponse force microcopy data, captured using the band-excitation (BE) technique, via Gaussian Process (GP) methods.

Computational Physics Materials Science

SFNet: Learning Object-aware Semantic Correspondence

no code implementations CVPR 2019 Junghyup Lee, Dohyung Kim, Jean Ponce, Bumsub Ham

We address the problem of semantic correspondence, that is, establishing a dense flow field between images depicting different instances of the same object or scene category.

Object Semantic correspondence

Squeezed Convolutional Variational AutoEncoder for Unsupervised Anomaly Detection in Edge Device Industrial Internet of Things

no code implementations18 Dec 2017 Dohyung Kim, Hyochang Yang, Minki Chung, Sungzoon Cho

In this paper, we propose Squeezed Convolutional Variational AutoEncoder (SCVAE) for anomaly detection in time series data for Edge Computing in Industrial Internet of Things (IIoT).

Edge-computing Time Series +2

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