Search Results for author:
Found 35 papers, 13 papers with code
Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution
Additionally, we find that learning on spatial domain does not convey the frequency content of the image, which is a crucial aspect in SISR.
Ranked #4 on
Image Super-Resolution
on Manga109 - 4x upscaling
OffsetBias: Leveraging Debiased Data for Tuning Evaluators
It is also known that such evaluators are vulnerable to biases, such as favoring longer responses.
Time-Efficient and Identity-Consistent Virtual Try-On Using A Variant of Altered Diffusion Models
This study discusses the critical issues of Virtual Try-On in contemporary e-commerce and the prospective metaverse, emphasizing the challenges of preserving intricate texture details and distinctive features of the target person and the clothes in various scenarios, such as clothing texture and identity characteristics like tattoos or accessories.
Instance Segmentation under Occlusions via Location-aware Copy-Paste Data Augmentation
Given the modest size of the dataset and the highly deformable nature of the objects to be segmented, this challenge demands the application of robust data augmentation techniques and wisely-chosen deep learning architectures.
Empowering Sentence Encoders with Prompting and Label Retrieval for Zero-shot Text Classification
With contrastive pre-training, sentence encoders are generally optimized to locate semantically similar samples closer to each other in their embedding spaces.
D-TensoRF: Tensorial Radiance Fields for Dynamic Scenes
We consider the radiance field of a dynamic scene as a 5D tensor.
RedPen: Region- and Reason-Annotated Dataset of Unnatural Speech
We present a novel speech dataset, RedPen, with human annotations on unnatural speech regions and their corresponding reasons.
Towards the Practical Utility of Federated Learning in the Medical Domain
We evaluate six FL algorithms designed for addressing data heterogeneity among clients, and a hybrid algorithm combining the strengths of two representative FL algorithms.
DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech
The majority of current Text-to-Speech (TTS) datasets, which are collections of individual utterances, contain few conversational aspects.
Revisiting the Importance of Amplifying Bias for Debiasing
$f_B$ is trained to focus on bias-aligned samples (i. e., overfitted to the bias) while $f_D$ is mainly trained with bias-conflicting samples by concentrating on samples which $f_B$ fails to learn, leading $f_D$ to be less susceptible to the dataset bias.
Uncertainty-Aware Text-to-Program for Question Answering on Structured Electronic Health Records
In addition, for a reliable EHR-QA model, we apply the uncertainty decomposition method to measure the ambiguity in the input question.
Question Answering for Complex Electronic Health Records Database using Unified Encoder-Decoder Architecture
An intelligent machine that can answer human questions based on electronic health records (EHR-QA) has a great practical value, such as supporting clinical decisions, managing hospital administration, and medical chatbots.
RankingMatch: Delving into Semi-Supervised Learning with Consistency Regularization and Ranking Loss
Semi-supervised learning (SSL) has played an important role in leveraging unlabeled data when labeled data is limited.
The effectiveness of feature attribution methods and its correlation with automatic evaluation scores
Explaining the decisions of an Artificial Intelligence (AI) model is increasingly critical in many real-world, high-stake applications.
STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech
Previous works on neural text-to-speech (TTS) have been addressed on limited speed in training and inference time, robustness for difficult synthesis conditions, expressiveness, and controllability.
CAP-GAN: Towards Adversarial Robustness with Cycle-consistent Attentional Purification
Adversarial attack is aimed at fooling the target classifier with imperceptible perturbation.
QuickBrowser: A Unified Model to Detect and Read Simple Object in Real-time
It also did a great job expectedly on the license-plate recognition task (on the AOLP dataset) by outperforming the current state-of-the-art method significantly in terms of recognition rate and inference time.
ReRankMatch: Semi-Supervised Learning with Semantics-Oriented Similarity Representation
We obtain promising results (4. 21% error rate on CIFAR-10 with 4000 labels, 22. 32% error rate on CIFAR-100 with 10000 labels, and 2. 19% error rate on SVHN with 1000 labels) when the amount of labeled data is sufficient to learn semantics-oriented similarity representation.
Adversarial Optimal Transport Through The Convolution Of Kernels With Evolving Measures
A novel algorithm is proposed to solve the sample-based optimal transport problem.
Explaining How Deep Neural Networks Forget by Deep Visualization
Explaining the behaviors of deep neural networks, usually considered as black boxes, is critical especially when they are now being adopted over diverse aspects of human life.
Simple Multi-Resolution Representation Learning for Human Pose Estimation
Our second approach allows learning during the process of feature extraction in which the heatmaps are generated at each resolution of the feature extractor.
Smart Inference for Multidigit Convolutional Neural Network based Barcode Decoding
SI considerably boosts accuracy and reduces the false prediction for trained models.
Applying Tensor Decomposition to image for Robustness against Adversarial Attack
However, it turns out a deep learning based model is highly vulnerable to some small perturbation called an adversarial attack.
Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencoder
We propose Unbalanced GANs, which pre-trains the generator of the generative adversarial network (GAN) using variational autoencoder (VAE).
Dissecting Catastrophic Forgetting in Continual Learning by Deep Visualization
Interpreting the behaviors of Deep Neural Networks (usually considered as a black box) is critical especially when they are now being widely adopted over diverse aspects of human life.
ContCap: A scalable framework for continual image captioning
After proving forgetting in image captioning, we propose various techniques to overcome the forgetting dilemma by taking a simple fine-tuning schema as the baseline.
DAPAS : Denoising Autoencoder to Prevent Adversarial attack in Semantic Segmentation
Nowadays, Deep learning techniques show dramatic performance on computer vision area, and they even outperform human.
TRk-CNN: Transferable Ranking-CNN for image classification of glaucoma, glaucoma suspect, and normal eyes
Although there is a Ranking-CNN that takes into account the ordinal classes, it cannot reflect the inter-class relationship to the final prediction.
T-Net: Nested encoder-decoder architecture for the main vessel segmentation in coronary angiography
As a result, all features from the low-level to the high-level extracted from the encoder are delivered from the beginning of the decoder to predict a more accurate mask.
Unsupervised classification into unknown number of classes
We propose a novel unsupervised classification method based on graph Laplacian.
Tournament Based Ranking CNN for the Cataract grading
Because the case with a serious degree is not quite usual, there are imbalance in number of dataset between severe case and normal cases of diseases.
2sRanking-CNN: A 2-stage ranking-CNN for diagnosis of glaucoma from fundus images using CAM-extracted ROI as an intermediate input
In this paper, we propose a 2-stage ranking-CNN that classifies fundus images as normal, suspicious, and glaucoma.
Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images
Pneumothorax is a relatively common disease, but in some cases, it may be difficult to find with chest radiography.
Automated detection of vulnerable plaque in intravascular ultrasound images
The ACS is usually related to coronary thrombosis and is primarily caused by plaque rupture followed by plaque erosion and calcified nodule.
ECG arrhythmia classification using a 2-D convolutional neural network
In this paper, we propose an effective electrocardiogram (ECG) arrhythmia classification method using a deep two-dimensional convolutional neural network (CNN) which recently shows outstanding performance in the field of pattern recognition.
