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 3501–3550 of 8378 papers

TitleStatusHype
SurfaceAug: Closing the Gap in Multimodal Ground Truth Sampling—0
Text Intimacy Analysis using Ensembles of Multilingual Transformers—0
Simplifying Neural Network Training Under Class ImbalanceCode0
Leveraging Domain Adaptation and Data Augmentation to Improve Qur'anic IR in English and Arabic—0
Learning Polynomial Problems with SL(2,R) Equivariance—0
FaultFormer: Pretraining Transformers for Adaptable Bearing Fault ClassificationCode0
TextAug: Test time Text Augmentation for Multimodal Person Re-identification—0
Developing Linguistic Patterns to Mitigate Inherent Human Bias in Offensive Language DetectionCode0
Re-Nerfing: Improving Novel View Synthesis through Novel View Synthesis—0
A Data-efficient Framework for Robotics Large-scale LiDAR Scene Parsing—0
Facial Emotion Recognition Under Mask Coverage Using a Data Augmentation TechniqueCode0
Robust Computer Vision in an Ever-Changing World: A Survey of Techniques for Tackling Distribution Shifts—0
Generating Images of the M87* Black Hole Using GANsCode0
Disentangling the Effects of Data Augmentation and Format Transform in Self-Supervised Learning of Image Representations—0
SASSL: Enhancing Self-Supervised Learning via Neural Style Transfer—0
Just-in-Time Detection of Silent Security Patches—0
Summarization-based Data Augmentation for Document ClassificationCode0
Learning from One Continuous Video Stream—0
Impact of Data Augmentation on QCNNs—0
TIDE: Test Time Few Shot Object DetectionCode0
Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental LearningCode0
DifAugGAN: A Practical Diffusion-style Data Augmentation for GAN-based Single Image Super-resolution—0
Easy Data Augmentation in Sentiment Analysis of Cyberbullying—0
DSS: Synthesizing long Digital Ink using Data augmentation, Style encoding and Split generation—0
Does VLN Pretraining Work with Nonsensical or Irrelevant Instructions?—0
An Investigation of Time Reversal Symmetry in Reinforcement LearningCode0
ScribbleGen: Generative Data Augmentation Improves Scribble-supervised Semantic SegmentationCode0
Comprehensive Benchmarking of Entropy and Margin Based Scoring Metrics for Data Selection—0
EucliDreamer: Fast and High-Quality Texturing for 3D Models with Stable Diffusion Depth—0
Reinforcement Learning from Diffusion Feedback: Q* for Image Search—0
VehicleGAN: Pair-flexible Pose Guided Image Synthesis for Vehicle Re-identification—0
SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image ClassificationCode0
Data Augmentation for Sample Efficient and Robust Document Ranking—0
AugmentTRAJ: A framework for point-based trajectory data augmentation—0
Identification of morphological fingerprint in perinatal brains using quasi-conformal mapping and contrastive learning—0
RandMSAugment: A Mixed-Sample Augmentation for Limited-Data Scenarios—0
nlpBDpatriots at BLP-2023 Task 2: A Transfer Learning Approach to Bangla Sentiment Analysis—0
Custom Data Augmentation for low resource ASR using Bark and Retrieval-Based Voice Conversion—0
Maximizing Discrimination Capability of Knowledge Distillation with Energy Function—0
A Parameterized Generative Adversarial Network Using Cyclic Projection for Explainable Medical Image ClassificationCode0
Robustness-Reinforced Knowledge Distillation with Correlation Distance and Network Pruning—0
Classifying cow stall numbers using YOLO—0
Tube-NeRF: Efficient Imitation Learning of Visuomotor Policies from MPC using Tube-Guided Data Augmentation and NeRFs—0
MAIRA-1: A specialised large multimodal model for radiology report generation—0
Curriculum Learning and Imitation Learning for Model-free Control on Financial Time-series—0
Test-Time Augmentation for 3D Point Cloud Classification and Segmentation—0
Masked Conditional Diffusion Models for Image Analysis with Application to Radiographic Diagnosis of Infant Abuse—0
Input Compression with Positional Consistency for Efficient Training and Inference of Transformer Neural NetworksCode0
Exploring Graph Classification Techniques Under Low Data Constraints: A Comprehensive Study—0
Stable Diffusion For Aerial Object Detection—0
Show:102550
← PrevPage 71 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