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 3801–3850 of 8378 papers

TitleStatusHype
Handling Rare Word Problem using Synthetic Training Data for Sinhala and Tamil Neural Machine Translation—0
Cross-speaker style transfer for text-to-speech using data augmentation—0
HandSeg: An Automatically Labeled Dataset for Hand Segmentation from Depth Images—0
Handwritten Amharic Character Recognition Using a Convolutional Neural Network—0
Boosting Automatic Exercise Evaluation Through Musculoskeletal Simulation-Based IMU Data Augmentation—0
Handwritten image augmentation—0
An improved helmet detection method for YOLOv3 on an unbalanced dataset—0
Advancing the Understanding of Fine-Grained 3D Forest Structures using Digital Cousins and Simulation-to-Reality: Methods and Datasets—0
DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models—0
HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation—0
HARD: Hard Augmentations for Robust Distillation—0
DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching—0
Dataset of Random Relaxations for Crystal Structure Search of Li-Si System—0
Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM—0
Augmentation Learning for Semi-Supervised Classification—0
Hardwiring ViT Patch Selectivity into CNNs using Patch Mixing—0
Boosting Adversarial Transferability with Spatial Adversarial Alignment—0
DiffPop: Plausibility-Guided Object Placement Diffusion for Image Composition—0
CSSL: Contrastive Self-Supervised Learning for Dependency Parsing on Relatively Free Word Ordered and Morphologically Rich Low Resource Languages—0
Harnessing Hard Mixed Samples with Decoupled Regularizer—0
CST5: Data augmentation for Code-Switched Semantic Parsing—0
Harnessing The Power of Attention For Patch-Based Biomedical Image Classification—0
An improved EfficientNetV2 for garbage classification—0
HARPT: A Corpus for Analyzing Consumers' Trust and Privacy Concerns in Mobile Health Apps—0
HaT5: Hate Language Identification using Text-to-Text Transfer Transformer—0
HateGAN: Adversarial Generative-Based Data Augmentation for Hate Speech Detection—0
HATERecognizer at SemEval-2019 Task 5: Using Features and Neural Networks to Face Hate Recognition—0
Hate Speech Detection in Limited Data Contexts using Synthetic Data Generation—0
Diff-Lung: Diffusion-Based Texture Synthesis for Enhanced Pathological Tissue Segmentation in Lung CT Scans—0
HCS at SemEval-2017 Task 5: Polarity detection in business news using convolutional neural networks—0
hdl2v: A Code Translation Dataset for Enhanced LLM Verilog Generation—0
CUDLE: Learning Under Label Scarcity to Detect Cannabis Use in Uncontrolled Environments—0
Boosted EfficientNet: Detection of Lymph Node Metastases in Breast Cancer Using Convolutional Neural Network—0
diffIRM: A Diffusion-Augmented Invariant Risk Minimization Framework for Spatiotemporal Prediction over Graphs—0
Differential Expression Analysis of Dynamical Sequencing Count Data with a Gamma Markov Chain—0
An Improved Deep Learning Approach For Product Recognition on Racks in Retail Stores—0
A Low-Overhead Incorporation-Extrapolation based Few-Shot CSI Feedback Framework for Massive MIMO Systems—0
HEp-2 Cell Image Classification with Deep Convolutional Neural Networks—0
Advancing Stuttering Detection via Data Augmentation, Class-Balanced Loss and Multi-Contextual Deep Learning—0
Improved Prosodic Clustering for Multispeaker and Speaker-independent Phoneme-level Prosody Control—0
Improved singing voice separation with chromagram-based pitch-aware remixing—0
Heterogeneous Graph Contrastive Learning with Spectral Augmentation—0
Curriculum-style Data Augmentation for LLM-based Metaphor Detection—0
Heterogeneous Recycle Generation for Chinese Grammatical Error Correction—0
Differential Diagnosis of Frontotemporal Dementia and Alzheimer's Disease using Generative Adversarial Network—0
HiBid: A Cross-Channel Constrained Bidding System with Budget Allocation by Hierarchical Offline Deep Reinforcement Learning—0
Boost AI Power: Data Augmentation Strategies with unlabelled Data and Conformal Prediction, a Case in Alternative Herbal Medicine Discrimination with Electronic Nose—0
DiffECG: A Versatile Probabilistic Diffusion Model for ECG Signals Synthesis—0
Boomerang: Local sampling on image manifolds using diffusion models—0
An Improved Data Augmentation Scheme for Model Predictive Control Policy Approximation—0
Show:102550
← PrevPage 77 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