the archive

#data augmentation

9 results

cs.CL2019

Is artificial data useful for biomedical Natural Language Processing algorithms?

Zixu Wang, Julia Ive, Sumithra Velupillai +1

The paper studies how artificially generated clinical text can be used to augment or replace real training data for biomedical NLP tasks, demonstrating performance gains in text cl…

#biomedical nlp#data augmentation#synthetic data#text classification

cs.CV2019

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

Sangdoo Yun, Dongyoon Han, Seong Joon Oh +3

The paper introduces CutMix, a data augmentation method that cuts patches from one image and pastes them onto another while mixing their labels, improving classification, localizat…

#data augmentation#regularization#image classification#object localization

cs.CV2019

Data Priming Network for Automatic Check-Out

Congcong Li, Dawei Du, Libo Zhang +5

The paper introduces a data priming network that improves visual item counting for automatic checkout by reducing background distractions and selecting realistic viewpoints, addres…

#automatic checkout#domain adaptation#data augmentation#object counting

cs.CV2019

Learning Raw Image Denoising with Bayer Pattern Unification and Bayer Preserving Augmentation

Jiaming Liu, Chi-Hao Wu, Yuzhi Wang +8

The paper proposes a Bayer pattern unification method and a Bayer-preserving augmentation technique to enable effective deep learning-based denoising of raw sensor images, achievin…

#raw image denoising#bayer pattern#data augmentation#deep learning

cs.CV2019

Safe Augmentation: Learning Task-Specific Transformations from Data

Irynei Baran, Orest Kupyn, Arseny Kravchenko

The paper proposes Safe Augmentation, a simple, model‑agnostic approach that learns task‑specific image transformations which preserve the data distribution and boost generalizatio…

#data augmentation#task-specific transformations#model fine-tuning#generalization

cs.CV2019

Hydranet: Data Augmentation for Regression Neural Networks

Florian Dubost, Gerda Bortsova, Hieab Adams +4

The paper presents Hydranet, a data‑augmentation method that creates new training samples by recombining existing medical images, improving regression neural networks that learn fr…

#data augmentation#regression neural networks#medical imaging#limited labeled data

eess.IV2019

A Two Stage GAN for High Resolution Retinal Image Generation and Segmentation

Paolo Andreini, Simone Bonechi, Monica Bianchini +3

The paper introduces a two‑stage GAN that first generates retinal vessel label maps and then translates them into high‑resolution retinal images, enabling data augmentation for ves…

#gan#retinal image synthesis#semantic segmentation#data augmentation

cs.CV2019

Segmenting Hyperspectral Images Using Spectral-Spatial Convolutional Neural Networks With Training-Time Data Augmentation

Jakub Nalepa, Lukasz Tulczyjew, Michal Myller +1

The paper proposes a spectral‑spatial convolutional neural network for segmenting hyperspectral images, employing extensive data augmentation to mitigate limited ground‑truth data…

#hyperspectral imaging#semantic segmentation#spectral-spatial CNN#data augmentation

cs.CV2019

DeepAtlas: Joint Semi-Supervised Learning of Image Registration and Segmentation

Zhenlin Xu, Marc Niethammer

The paper introduces DeepAtlas, a deep learning framework that jointly learns image registration and segmentation in a semi‑supervised way, allowing high‑quality 3D medical image a…

#joint registration and segmentation#semi-supervised learning#medical imaging#3d mri