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 1–50 of 308 papers

TitleStatusHype
Detectron2 Object Detection & Manipulating Images using CartoonizationCode4
AutoAugment: Learning Augmentation Policies from DataCode3
Differentiable Data Augmentation with KorniaCode3
UniMERNet: A Universal Network for Real-World Mathematical Expression RecognitionCode3
CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documentsCode2
Deep PCB To COCO ConvertorCode2
Random Erasing Data AugmentationCode2
XoFTR: Cross-modal Feature Matching TransformerCode2
When Large Multimodal Models Confront Evolving Knowledge:Challenges and PathwaysCode2
Diffusion-Enhanced Test-time Adaptation with Text and Image AugmentationCode2
Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object DetectionCode2
A Survey on Data Augmentation in Large Model EraCode2
Diversify Your Vision Datasets with Automatic Diffusion-Based AugmentationCode1
Adversarial Policy Gradient for Deep Learning Image AugmentationCode1
Prompt-Free Conditional Diffusion for Multi-object Image AugmentationCode1
Adversarial Instance Augmentation for Building Change Detection in Remote Sensing ImagesCode1
Masked Autoencoders are Robust Data AugmentorsCode1
MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision TransformerCode1
Salient Objects in ClutterCode1
InAugment: Improving Classifiers via Internal AugmentationCode1
Improving the Transferability of Adversarial Samples by Path-Augmented MethodCode1
Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric LearningCode1
Improved Regularization of Convolutional Neural Networks with CutoutCode1
Learn to Augment: Joint Data Augmentation and Network Optimization for Text RecognitionCode1
Anatomical Data Augmentation via Fluid-based Image RegistrationCode1
DIAGen: Diverse Image Augmentation with Generative ModelsCode1
Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce ClassificationCode1
Multi-Disease Detection in Retinal Imaging based on Ensembling Heterogeneous Deep Learning ModelsCode1
An Open-source Tool for Hyperspectral Image Augmentation in TensorflowCode1
Diversified in-domain synthesis with efficient fine-tuning for few-shot classificationCode1
Kornia: an Open Source Differentiable Computer Vision Library for PyTorchCode1
Generative Adversarial Networks for Image Augmentation in Agriculture: A Systematic ReviewCode1
Can AI help in screening Viral and COVID-19 pneumonia?Code1
CamDiff: Camouflage Image Augmentation via Diffusion ModelCode1
Image Augmentation for Multitask Few-Shot Learning: Agricultural Domain Use-CaseCode1
FitVid: Overfitting in Pixel-Level Video PredictionCode1
An Analysis on Ensemble Learning optimized Medical Image Classification with Deep Convolutional Neural NetworksCode1
CLAP: Isolating Content from Style through Contrastive Learning with Augmented PromptsCode1
Fast AutoAugmentCode1
Data Augmentation Based Malware Detection using Convolutional Neural NetworksCode1
Image, Text, and Speech Data Augmentation using Multimodal LLMs for Deep Learning: A SurveyCode1
Implicit Semantic Data Augmentation for Deep NetworksCode1
An Efficient and Scalable Deep Learning Approach for Road Damage DetectionCode1
Data Augmentation for Scene Text RecognitionCode1
Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse InputCode1
AugNet: End-to-End Unsupervised Visual Representation Learning with Image AugmentationCode1
FSCE: Few-Shot Object Detection via Contrastive Proposal EncodingCode1
AAPL: Adding Attributes to Prompt Learning for Vision-Language ModelsCode1
Learning Data Augmentation Strategies for Object DetectionCode1
GANSeg: Learning to Segment by Unsupervised Hierarchical Image GenerationCode1
Show:102550
← PrevPage 1 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AugstaticBalanced Accuracy0—Unverified