Search Results for author:
Found 15 papers, 8 papers with code
PSYDIAL: Personality-based Synthetic Dialogue Generation using Large Language Models
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.
Why Is It Hate Speech? Masked Rationale Prediction for Explainable Hate Speech Detection
In a hate speech detection model, we should consider two critical aspects in addition to detection performance-bias and explainability.
Ranked #1 on
Hate Speech Detection
on HateXplain
Dataset Bias Prediction for Few-Shot Image Classification
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.
Decomposing Texture and Semantics for Out-of-distribution Detection
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?
From a safety perspective, a machine learning method embedded in real-world applications is required to distinguish irregular situations.
How Positive Are You: Text Style Transfer using Adaptive Style Embedding
In both approaches, however, it is impossible to adjust the strength of the style in the generated output.
Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network
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.
NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results
This paper reviews the NTIRE 2020 challenge on real world super-resolution.
SimUSR: A Simple but Strong Baseline for Unsupervised Image Super-resolution
In this paper, we tackle a fully unsupervised super-resolution problem, i. e., neither paired images nor ground truth HR images.
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy
The key intuition of CutBlur is to enable a model to learn not only "how" but also "where" to super-resolve an image.
Efficient Deep Neural Network for Photo-realistic Image Super-Resolution
Recent progress in deep learning-based models has improved photo-realistic (or perceptual) single-image super-resolution significantly.
Image Distortion Detection using Convolutional Neural Network
Image distortion classification and detection is an important task in many applications.
Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network
In recent years, deep learning methods have been successfully applied to single-image super-resolution tasks.
Ranked #17 on
Image Super-Resolution
on BSD100 - 2x upscaling
Investigating the feature collection for semantic segmentation via single skip connection
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.
Enhancing the Performance of Convolutional Neural Networks on Quality Degraded Datasets
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.
