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 21–30 of 308 papers

TitleStatusHype
Diversify Your Vision Datasets with Automatic Diffusion-Based AugmentationCode1
MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision TransformerCode1
CamDiff: Camouflage Image Augmentation via Diffusion ModelCode1
Improving the Transferability of Adversarial Samples by Path-Augmented MethodCode1
Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric LearningCode1
Self-adversarial Multi-scale Contrastive Learning for Semantic Segmentation of Thermal Facial ImagesCode1
Masked Autoencoders are Robust Data AugmentorsCode1
Generative Adversarial Networks for Image Augmentation in Agriculture: A Systematic ReviewCode1
TorMentor: Deterministic dynamic-path, data augmentations with fractalsCode1
Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse InputCode1
Show:102550
← PrevPage 3 of 31Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AugstaticBalanced Accuracy0—Unverified