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 51–60 of 308 papers

TitleStatusHype
Adversarial Instance Augmentation for Building Change Detection in Remote Sensing ImagesCode1
Diversified in-domain synthesis with efficient fine-tuning for few-shot classificationCode1
Salient Objects in ClutterCode1
SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual PoliciesCode1
Adversarial Policy Gradient for Deep Learning Image AugmentationCode1
Data Augmentation Based Malware Detection using Convolutional Neural NetworksCode1
GANSeg: Learning to Segment by Unsupervised Hierarchical Image GenerationCode1
Swin Transformer with Enhanced Dropout and Layer-wise Unfreezing for Facial Expression Recognition in Mental Health DetectionCode1
AAPL: Adding Attributes to Prompt Learning for Vision-Language ModelsCode1
Improved Regularization of Convolutional Neural Networks with CutoutCode1
Show:102550
← PrevPage 6 of 31Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AugstaticBalanced Accuracy0—Unverified