SOTAVerified

Data Augmentation

Data augmentation involves techniques used for increasing the amount of data, based on different modifications, to expand the amount of examples in the original dataset. Data augmentation not only helps to grow the dataset but it also increases the diversity of the dataset. When training machine learning models, data augmentation acts as a regularizer and helps to avoid overfitting.

Data augmentation techniques have been found useful in domains like NLP and computer vision. In computer vision, transformations like cropping, flipping, and rotation are used. In NLP, data augmentation techniques can include swapping, deletion, random insertion, among others.

Further readings:

( Image credit: Albumentations )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 6151–6200 of 8378 papers

TitleStatusHype
Learning Pose Grammar for Monocular 3D Pose Estimation—0
Benchmarking Augmentation Methods for Learning Robust Navigation Agents: the Winning Entry of the 2021 iGibson Challenge—0
Learning Robust Feature Representations for Scene Text Detection—0
Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks—0
Learning Sequential Information in Task-based fMRI for Synthetic Data Augmentation—0
Learning Temporal Embeddings for Complex Video Analysis—0
Learning the Localization Function: Machine Learning Approach to Fingerprinting Localization—0
Learning the Non-linearity in Convolutional Neural Networks—0
Learning to Ask Unanswerable Questions for Machine Reading Comprehension—0
Learning to Augment for Casual User Recommendation—0
Learning to Augment Influential Data—0
Learning to Augment via Implicit Differentiation for Domain Generalization—0
Learning to Detect Every Thing in an Open World—0
Learning to Detect Instantaneous Changes with Retrospective Convolution and Static Sample Synthesis—0
Learning to Drive by Imitating Surrounding Vehicles—0
Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networks—0
Learning to Find Missing Video Frames with Synthetic Data Augmentation: A General Framework and Application in Generating Thermal Images Using RGB Cameras—0
Learning to Generate Examples for Semantic Processing Tasks—0
Learning to Generate Novel Classes for Deep Metric Learning—0
Learning to Generate Synthetic Data via Compositing—0
Learning to Hear Broken Motors: Signature-Guided Data Augmentation for Induction-Motor Diagnostics—0
Learning to Identify Drilling Defects in Turbine Blades with Single Stage Detectors—0
Learning to Ignore Adversarial Attacks—0
Learning to Ignore Adversarial Attacks—0
Learning to mask: Towards generalized face forgery detection—0
Learning to Rank Question Answer Pairs with Bilateral Contrastive Data Augmentation—0
Learning to Refine Human Pose Estimation—0
Learning towards Selective Data Augmentation for Dialogue Generation—0
Learning Transferable Object-Centric Diffeomorphic Transformations for Data Augmentation in Medical Image Segmentation—0
Learning under selective labels in the presence of expert consistency—0
Teaching What You Should Teach: A Data-Based Distillation Method—0
Learning with Exact Invariances in Polynomial Time—0
Toward Robust Graph Semi-Supervised Learning against Extreme Data Scarcity—0
Learning with invariances in random features and kernel models—0
Learning with Limited Text Data—0
Learn to Code-Switch: Data Augmentation using Copy Mechanism on Language Modeling—0
LEAVES: Learning Views for Time-Series Data in Contrastive Learning—0
LeCun at SemEval-2021 Task 6: Detecting Persuasion Techniques in Text Using Ensembled Pretrained Transformers and Data Augmentation—0
Led3D: A Lightweight and Efficient Deep Approach to Recognizing Low-Quality 3D Faces—0
LENS: Localization enhanced by NeRF synthesis—0
LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations—0
LesionAid: Vision Transformers-based Skin Lesion Generation and Classification—0
Lesion Conditional Image Generation for Improved Segmentation of Intracranial Hemorrhage from CT Images—0
Less is More: Unsupervised Mask-guided Annotated CT Image Synthesis with Minimum Manual Segmentations—0
Let's Get Dirty: GAN Based Data Augmentation for Camera Lens Soiling Detection in Autonomous Driving—0
Leveraging Affective Bidirectional Transformers for Offensive Language Detection—0
Leveraging AI Graders for Missing Score Imputation to Achieve Accurate Ability Estimation in Constructed-Response Tests—0
Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations—0
Leveraging Causal Inference for Explainable Automatic Program Repair—0
Leveraging Clinically Relevant Biometric Constraints To Supervise A Deep Learning Model For The Accurate Caliper Placement To Obtain Sonographic Measurements Of The Fetal Brain—0
Show:102550
← PrevPage 124 of 168Next →
All datasetsImageNetCIFAR-10GA1457

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DeiT-B (+MixPro)Accuracy (%)82.9—Unverified
2ResNet-200 (DeepAA)Accuracy (%)81.32—Unverified
3DeiT-S (+MixPro)Accuracy (%)81.3—Unverified
4ResNet-200 (Fast AA)Accuracy (%)80.6—Unverified
5ResNet-200 (UA)Accuracy (%)80.4—Unverified
6ResNet-200 (AA)Accuracy (%)80—Unverified
7ResNet-50 (DeepAA)Accuracy (%)78.3—Unverified
8ResNet-50 (TA wide)Accuracy (%)78.07—Unverified
9ResNet-50 (LoRot-E)Accuracy (%)77.72—Unverified
10ResNet-50 (LoRot-I)Accuracy (%)77.71—Unverified
#ModelMetricClaimedVerifiedStatus
1WideResNet-40-2 (Faster AA)Percentage error3.7—Unverified
2Shake-Shake (26 2×32d) (Faster AA)Percentage error2.7—Unverified
3WideResNet-28-10 (Faster AA)Percentage error2.6—Unverified
4Shake-Shake (26 2×112d) (Faster AA)Percentage error2—Unverified
5Shake-Shake (26 2×96d) (Faster AA)Percentage error2—Unverified
#ModelMetricClaimedVerifiedStatus
1DiffAugClassification Accuracy92.7—Unverified
2PaCMAPClassification Accuracy85.3—Unverified
3hNNEClassification Accuracy77.4—Unverified
4TopoAEClassification Accuracy74.6—Unverified