Search Results for author: Kyung-Ah Sohn

Found 15 papers, 9 papers with code

PSYDIAL: Personality-based Synthetic Dialogue Generation using Large Language Models

1 code implementation1 Apr 2024 Ji-Eun Han, Jun-Seok Koh, Hyeon-Tae Seo, Du-Seong Chang, Kyung-Ah Sohn

Experimental results indicate that while pre-trained models and those fine-tuned with a chit-chat dataset struggle to generate responses reflecting personality, models trained with PSYDIAL show significant improvements.

Dialogue Generation

Why Is It Hate Speech? Masked Rationale Prediction for Explainable Hate Speech Detection

1 code implementation COLING 2022 Jiyun Kim, Byounghan Lee, Kyung-Ah Sohn

In a hate speech detection model, we should consider two critical aspects in addition to detection performance-bias and explainability.

Hate Speech Detection Sentence

Dataset Bias Prediction for Few-Shot Image Classification

no code implementations29 Sep 2021 Jangwook Kim, Kyung-Ah Sohn

Once the features are extracted from an image data, the bias prediction network tries to recover the bias of the raw image such as color from the features.

Classification Few-Shot Image Classification +1

Decomposing Texture and Semantics for Out-of-distribution Detection

no code implementations29 Sep 2021 Jeong-Hyeon Moon, Namhyuk Ahn, Kyung-Ah Sohn

Out-of-distribution (OOD) detection has made significant progress in recent years because the distribution mismatch between the training and testing can severely deteriorate the reliability of a machine learning system. Nevertheless, the lack of precise interpretation of the in-distribution limits the application of OOD detection methods to real-world system pipielines.

Out-of-Distribution Detection Out of Distribution (OOD) Detection +1

What is Wrong with One-Class Anomaly Detection?

1 code implementation20 Apr 2021 JuneKyu Park, Jeong-Hyeon Moon, Namhyuk Ahn, Kyung-Ah Sohn

From a safety perspective, a machine learning method embedded in real-world applications is required to distinguish irregular situations.

Anomaly Detection

How Positive Are You: Text Style Transfer using Adaptive Style Embedding

1 code implementation COLING 2020 Heejin Kim, Kyung-Ah Sohn

In both approaches, however, it is impossible to adjust the strength of the style in the generated output.

Disentanglement Sentence +3

Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network

1 code implementation30 Sep 2020 Sijin Kim, Namhyuk Ahn, Kyung-Ah Sohn

Viewing in a different point of combining, we introduce a spatially-heterogeneous distortion dataset in which multiple corruptions are applied to the different locations of each image.

Multi-Task Learning

SimUSR: A Simple but Strong Baseline for Unsupervised Image Super-resolution

no code implementations23 Apr 2020 Namhyuk Ahn, Jaejun Yoo, Kyung-Ah Sohn

In this paper, we tackle a fully unsupervised super-resolution problem, i. e., neither paired images nor ground truth HR images.

Denoising Image Super-Resolution +1

Efficient Deep Neural Network for Photo-realistic Image Super-Resolution

1 code implementation6 Mar 2019 Namhyuk Ahn, Byungkon Kang, Kyung-Ah Sohn

Recent progress in deep learning-based models has improved photo-realistic (or perceptual) single-image super-resolution significantly.

Image Super-Resolution

Investigating the feature collection for semantic segmentation via single skip connection

no code implementations23 Oct 2017 Jonghwa Yim, Kyung-Ah Sohn

Therefore, in this study, we exhaustively research skip connections of state-of-the-art deep convolutional networks and investigate the characteristics of the features from each intermediate layer.

Object object-detection +2

Enhancing the Performance of Convolutional Neural Networks on Quality Degraded Datasets

no code implementations18 Oct 2017 Jonghwa Yim, Kyung-Ah Sohn

Despite the appeal of deep neural networks that largely replace the traditional handmade filters, they still suffer from isolated cases that cannot be properly handled only by the training of convolutional filters.

Image Classification

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