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 5951–6000 of 8378 papers

TitleStatusHype
DeepMix: Online Auto Data Augmentation for Robust Visual Object Tracking—0
TITAN: T Cell Receptor Specificity Prediction with Bimodal Attention Networks—0
Disfluency Detection with Unlabeled Data and Small BERT Models—0
Exploring 2D Data Augmentation for 3D Monocular Object Detection—0
PALI at SemEval-2021 Task 2: Fine-Tune XLM-RoBERTa for Word in Context Disambiguation—0
GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical ReviewCode0
Boosting Masked Face Recognition with Multi-Task ArcFace—0
Does enhanced shape bias improve neural network robustness to common corruptions?—0
Estimating Traffic Speeds using Probe Data: A Deep Neural Network Approach—0
Automatic Stroke Classification of Tabla Accompaniment in Hindustani Vocal Concert Audio—0
Machine-learning-based head impact subtyping based on the spectral densities of the measurable head kinematics—0
A Competitive Method to VIPriors Object Detection Challenge—0
ECACL: A Holistic Framework for Semi-Supervised Domain AdaptationCode1
Few-shot learning via tensor hallucinationCode0
GPT3Mix: Leveraging Large-scale Language Models for Text AugmentationCode1
Combining a Convolutional Neural Network with Autoencoders to Predict the Survival Chance of COVID-19 Patients—0
On Training Sketch Recognizers for New Domains—0
Best Practices for Noise-Based Augmentation to Improve the Performance of Deployable Speech-Based Emotion Recognition Systems—0
SimCSE: Simple Contrastive Learning of Sentence EmbeddingsCode2
A Full Text-Dependent End to End Mispronunciation Detection and Diagnosis with Easy Data Augmentation TechniquesCode1
Sentence Concatenation Approach to Data Augmentation for Neural Machine Translation—0
Color Variants Identification in Fashion e-commerce via Contrastive Self-Supervised Representation Learning—0
Age Range Estimation using MTCNN and VGG-Face Model—0
Hierarchical Topic Presence Models—0
Data Augmentation for Voice-Assistant NLU using BERT-based Interchangeable Rephrase—0
Open data for Moroccan license plates for OCR applications : data collection, labeling, and model construction—0
EnvGAN: Adversarial Synthesis of Environmental Sounds for Data Augmentation—0
A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data AugmentationCode1
On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world NoiseCode0
Representative Forgery Mining for Fake Face DetectionCode1
Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling—0
Can a Transformer Pass the Wug Test? Tuning Copying Bias in Neural Morphological Inflection Models—0
Exploring Geometric Consistency for Monocular 3D Object Detection—0
Generalization bounds via distillation—0
Neural Camera SimulatorsCode1
Noether: The More Things Change, the More Stay the Same—0
Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-AugmentationCode1
Fruit Quality and Defect Image Classification with Conditional GAN Data AugmentationCode1
Constructing Contrastive samples via Summarization for Text Classification with limited annotationsCode0
Raindrops on Windshield: Dataset and Lightweight Gradient-Based Detection AlgorithmCode1
ALT-MAS: A Data-Efficient Framework for Active Testing of Machine Learning Algorithms—0
RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes—0
The NTNU Taiwanese ASR System for Formosa Speech Recognition Challenge 2020—0
Robust Training of Social Media Image Classification Models for Rapid Disaster Response—0
Direct Differentiable Augmentation SearchCode1
Handling Climate Change Using Counterfactuals: Using Counterfactuals in Data Augmentation to Predict Crop Growth in an Uncertain Climate Future—0
Exploring Machine Speech Chain for Domain Adaptation and Few-Shot Speaker Adaptation—0
Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxicCode0
CutPaste: Self-Supervised Learning for Anomaly Detection and LocalizationCode1
Analysis Towards Classification of Infection and Ischaemia of Diabetic Foot Ulcers—0
Show:102550
← PrevPage 120 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