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 41–50 of 308 papers

TitleStatusHype
A Novel Breast Ultrasound Image Augmentation Method Using Advanced Neural Style Transfer: An Efficient and Explainable Approach—0
SRA: A Novel Method to Improve Feature Embedding in Self-supervised Learning for Histopathological Images—0
Few-shot target-driven instance detection based on open-vocabulary object detection models—0
Automated Segmentation and Analysis of Microscopy Images of Laser Powder Bed Fusion Melt Tracks—0
Towards Data-Centric Face Anti-Spoofing: Improving Cross-domain Generalization via Physics-based Data SynthesisCode0
Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce ClassificationCode1
DIAGen: Diverse Image Augmentation with Generative ModelsCode1
LowCLIP: Adapting the CLIP Model Architecture for Low-Resource Languages in Multimodal Image Retrieval TaskCode0
Enhancing Autonomous Vehicle Perception in Adverse Weather through Image Augmentation during Semantic Segmentation TrainingCode0
Learning deep illumination-robust features from multispectral filter array imagesCode0
Show:102550
← PrevPage 5 of 31Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AugstaticBalanced Accuracy0—Unverified