SOTAVerified

Image Augmentation

Image Augmentation is a data augmentation method that generates more training data from the existing training samples. Image Augmentation is especially useful in domains where training data is limited or expensive to obtain like in biomedical applications.

Source: Improved Image Augmentation for Convolutional Neural Networks by Copyout and CopyPairing

( Image credit: Kornia )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 276–300 of 308 papers

TitleStatusHype
Application of Facial Recognition using Convolutional Neural Networks for Entry Access ControlCode0
Random Transformation of Image Brightness for Adversarial AttackCode0
Learning Convolutional Neural Networks using Hybrid Orthogonal Projection and EstimationCode0
DenseNet Models for Tiny ImageNet ClassificationCode0
Learning deep illumination-robust features from multispectral filter array imagesCode0
Siamese Networks for Cat Re-Identification: Exploring Neural Models for Cat Instance RecognitionCode0
Learning Optimal Data Augmentation Policies via Bayesian Optimization for Image Classification TasksCode0
Learning Raw Image Denoising with Bayer Pattern Unification and Bayer Preserving AugmentationCode0
Augmentor: An Image Augmentation Library for Machine LearningCode0
Learning to Compose Domain-Specific Transformations for Data AugmentationCode0
VIIS: Visible and Infrared Information Synthesis for Severe Low-light Image EnhancementCode0
Data Augmentation via Levy ProcessesCode0
A machine-generated catalogue of Charon's craters and implications for the Kuiper beltCode0
Sparse Signal Models for Data Augmentation in Deep Learning ATRCode0
Long Tail Image Generation Through Feature Space Augmentation and Iterated LearningCode0
LowCLIP: Adapting the CLIP Model Architecture for Low-Resource Languages in Multimodal Image Retrieval TaskCode0
Data Augmentation using Random Image Cropping and Patching for Deep CNNsCode0
Towards Data-Centric Face Anti-Spoofing: Improving Cross-domain Generalization via Physics-based Data SynthesisCode0
MGAug: Multimodal Geometric Augmentation in Latent Spaces of Image DeformationsCode0
Reweighting Augmented Samples by Minimizing the Maximal Expected LossCode0
Zero-Shot Learning by Harnessing Adversarial SamplesCode0
SAC-GAN: Structure-Aware Image CompositionCode0
Compound Figure Separation of Biomedical Images: Mining Large Datasets for Self-supervised LearningCode0
MLN-net: A multi-source medical image segmentation method for clustered microcalcifications using multiple layer normalizationCode0
CFR-ICL: Cascade-Forward Refinement with Iterative Click Loss for Interactive Image SegmentationCode0
Show:102550
← PrevPage 12 of 13Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AugstaticBalanced Accuracy0—Unverified