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 2851–2900 of 8378 papers

TitleStatusHype
Pseudo-Bag Mixup Augmentation for Multiple Instance Learning-Based Whole Slide Image Classification—0
Improving Primate Sounds Classification using Binary Presorting for Deep Learning—0
Cross Spectral Image Reconstruction Using a Deep Guided Neural NetworkCode0
Neural Bayes estimators for censored inference with peaks-over-threshold modelsCode1
Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection—0
On the Usefulness of Synthetic Tabular Data Generation—0
TranssionADD: A multi-frame reinforcement based sequence tagging model for audio deepfake detection—0
Enhancing Representation Learning on High-Dimensional, Small-Size Tabular Data: A Divide and Conquer Method with Ensembled VAEs—0
Using Large Language Models to Provide Explanatory Feedback to Human Tutors—0
Accelerating Molecular Graph Neural Networks via Knowledge Distillation—0
Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion RecognitionCode1
Pseudo-Trilateral Adversarial Training for Domain Adaptive Traversability Prediction—0
Few-Shot Continual Learning via Flat-to-Wide ApproachesCode0
Chain-of-Thought Prompt Distillation for Multimodal Named Entity Recognition and Multimodal Relation Extraction—0
Semi-supervised Object Detection: A Survey on Recent Research and Progress—0
A Web-based Mpox Skin Lesion Detection System Using State-of-the-art Deep Learning Models Considering Racial DiversityCode0
Towards Robust Aspect-based Sentiment Analysis through Non-counterfactual Augmentations—0
Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language TasksCode0
Unsupervised Deformable Ultrasound Image Registration and Its Application for Vessel Segmentation—0
Harnessing Data Augmentation to Quantify Uncertainty in the Early Estimation of Single-Photon Source QualityCode0
AugDMC: Data Augmentation Guided Deep Multiple ClusteringCode0
Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement LearningCode1
Data augmentation and refinement for recommender system: A semi-supervised approach using maximum margin matrix factorization—0
A systematic approach to deep learning-based nodule detection in chest radiographsCode1
Concurrent ischemic lesion age estimation and segmentation of CT brain using a Transformer-based network—0
End-to-End Augmentation Hyperparameter Tuning for Self-Supervised Anomaly Detection—0
Recent Advances in Direct Speech-to-text Translation—0
MultiEarth 2023 Deforestation Challenge -- Team FOREVER—0
A Novel Counterfactual Data Augmentation Method for Aspect-Based Sentiment Analysis—0
Deep Learning of Dynamical System Parameters from Return Maps as ImagesCode0
PAC-Chernoff Bounds: Understanding Generalization in the Interpolation Regime—0
Human Limits in Machine Learning: Prediction of Plant Phenotypes Using Soil Microbiome DataCode0
DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic ModelCode1
Improving Generalizability of Graph Anomaly Detection Models via Data AugmentationCode1
Semi-Supervised Learning for Multi-Label Cardiovascular Diseases Prediction:A Multi-Dataset Study—0
MTN: Forensic Analysis of MP4 Video Files Using Graph Neural NetworksCode0
Investigating Masking-based Data Generation in Language Models—0
Low-Resource Text-to-Speech Using Specific Data and Noise Augmentation—0
Semi-supervised Relation Extraction via Data Augmentation and Consistency-training—0
SLACK: Stable Learning of Augmentations with Cold-start and KL regularization—0
Cross-Modal Video to Body-joints Augmentation for Rehabilitation Exercise Quality Assessment—0
Improving Reading Comprehension Question Generation with Data Augmentation and Overgenerate-and-rankCode0
Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language ModelsCode0
A Simple Data Augmentation for Feature Distribution Skewed Federated Learning—0
Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentation—0
VIBR: Learning View-Invariant Value Functions for Robust Visual Control—0
SaliencyCut: Augmenting Plausible Anomalies for Anomaly Detection—0
Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization ApproachCode0
Learning Cross-lingual Mappings for Data Augmentation to Improve Low-Resource Speech Recognition—0
Data Augmentation for Seizure Prediction with Generative Diffusion Model—0
Show:102550
← PrevPage 58 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