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 1951–2000 of 8378 papers

TitleStatusHype
End-to-End Action Segmentation Transformer—0
An Empirical Study of Causal Relation Extraction Transfer: Design and Data—0
Removing Geometric Bias in One-Class Anomaly Detection with Adaptive Feature PerturbationCode0
Disconnect to Connect: A Data Augmentation Method for Improving Topology Accuracy in Image SegmentationCode0
From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning—0
SAS: Segment Anything Small for Ultrasound -- A Non-Generative Data Augmentation Technique for Robust Deep Learning in Ultrasound Imaging—0
Image Data Augmentation for the TAIGA-IACT Experiment with Conditional Generative Adversarial Networks—0
HILGEN: Hierarchically-Informed Data Generation for Biomedical NER Using Knowledgebases and Large Language Models—0
Using Test-Time Data Augmentation for Cross-Domain Atrial Fibrillation Detection from ECG Signals—0
Augmentation-Based Deep Learning for Identification of Circulating Tumor Cells—0
Towards Robust Universal Information Extraction: Benchmark, Evaluation, and Solution—0
Effective LLM Knowledge Learning via Model Generalization—0
DeepGrav: Anomalous Gravitational-Wave Detection Through Deep Latent FeaturesCode0
Rethinking Few-Shot Medical Image Segmentation by SAM2: A Training-Free Framework with Augmentative Prompting and Dynamic Matching—0
Synthetic Data Augmentation for Enhancing Harmful Algal Bloom Detection with Machine LearningCode0
Automatic Drywall Analysis for Progress Tracking and Quality Control in Construction—0
TopoMortar: A dataset to evaluate image segmentation methods focused on topology accuracyCode0
Class-Aware PillarMix: Can Mixed Sample Data Augmentation Enhance 3D Object Detection with Radar Point Clouds?—0
Limited Effectiveness of LLM-based Data Augmentation for COVID-19 Misinformation Stance Detection—0
Memorize or Generalize? Evaluating LLM Code Generation with Evolved Questions—0
BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling—0
Exploring Token-Level Augmentation in Vision Transformer for Semi-Supervised Semantic SegmentationCode0
A Generalized Theory of Mixup for Structure-Preserving Synthetic DataCode0
Data Augmentation for NeRFs in the Low Data Limit—0
Random Walks in Self-supervised Learning for Triangular Meshes—0
AI-Augmented Thyroid Scintigraphy for Robust Classification—0
A data augmentation strategy for deep neural networks with application to epidemic modelling—0
MIDAS: Mixing Ambiguous Data with Soft Labels for Dynamic Facial Expression Recognition—0
Style Content Decomposition-based Data Augmentation for Domain Generalizable Medical Image SegmentationCode0
UoR-NCL at SemEval-2025 Task 1: Using Generative LLMs and CLIP Models for Multilingual Multimodal Idiomaticity RepresentationCode0
Language-Informed Hyperspectral Image Synthesis for Imbalanced-Small Sample Classification via Semi-Supervised Conditional Diffusion Model—0
Learning with Exact Invariances in Polynomial Time—0
cMIM: A Contrastive Mutual Information Framework for Unified Generative and Discriminative Representation Learning—0
Teaching Dense Retrieval Models to Specialize with Listwise Distillation and LLM Data AugmentationCode0
Order Doesn't Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation—0
SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data AugmentationCode0
Graph Augmentation for Cross Graph Domain Generalization—0
Iterative Counterfactual Data AugmentationCode0
Robust Polyp Detection and Diagnosis through Compositional Prompt-Guided Diffusion Models—0
MAGE: Multi-Head Attention Guided Embeddings for Low Resource Sentiment Classification—0
Your Language Model May Think Too Rigidly: Achieving Reasoning Consistency with Symmetry-Enhanced Training—0
Easy-Poly: A Easy Polyhedral Framework For 3D Multi-Object Tracking—0
Contrastive Visual Data Augmentation—0
GCC: Generative Color Constancy via Diffusing a Color Checker—0
On Neural Inertial Classification Networks for Pedestrian Activity Recognition—0
SQLong: Enhanced NL2SQL for Longer Contexts with LLMs—0
USegMix: Unsupervised Segment Mix for Efficient Data Augmentation in Pathology Images—0
Physics-Informed Gradient Estimation for Accelerating Deep Learning based AC-OPF—0
Patch Stitching Data Augmentation for Cancer Classification in Pathology Images—0
Enhancing LLMs for Identifying and Prioritizing Important Medical Jargons from Electronic Health Record Notes Utilizing Data Augmentation—0
Show:102550
← PrevPage 40 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