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 4451–4500 of 8378 papers

TitleStatusHype
Strategies to Improve Few-shot Learning for Intent Classification and Slot-Filling—0
Stride and Translation Invariance in CNNs—0
Structural Similarity: When to Use Deep Generative Models on Imbalanced Image Dataset Augmentation—0
Structure-enhanced Contrastive Learning for Graph Clustering—0
Struct-X: Enhancing Large Language Models Reasoning with Structured Data—0
Study and development of a Computer-Aided Diagnosis system for classification of chest x-ray images using convolutional neural networks pre-trained for ImageNet and data augmentation—0
Studying Robustness of Semantic Segmentation under Domain Shift in cardiac MRI—0
Study of Encoder-Decoder Architectures for Code-Mix Search Query Translation—0
Style Augmentation improves Medical Image Segmentation—0
StyleAugment: Learning Texture De-biased Representations by Style Augmentation without Pre-defined Textures—0
Style Feature Extraction Using Contrastive Conditioned Variational Autoencoders with Mutual Information Constraints—0
StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer—0
Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis—0
StyleTime: Style Transfer for Synthetic Time Series Generation—0
Style transfer as data augmentation: evaluating unpaired image-to-image translation models in mammography—0
Data augmentation in microscopic images for material data mining—0
Style transfer-based image synthesis as an efficient regularization technique in deep learning—0
Stylistic Retrieval-based Dialogue System with Unparallel Training Data—0
Sub-corpora Sampling with an Application to Bilingual Lexicon Extraction—0
Subject-based Non-contrastive Self-Supervised Learning for ECG Signal Processing—0
Submission to ActivityNet Challenge 2019: Task B Spatio-temporal Action Localization—0
Subsampled Turbulence Removal Network—0
Automatic kidney segmentation in ultrasound images using subsequent boundary distance regression and pixelwise classification networks—0
SUBS: Subtree Substitution for Compositional Semantic Parsing—0
SubstationAI: Multimodal Large Model-Based Approaches for Analyzing Substation Equipment Faults—0
Substructure Substitution: Structured Data Augmentation for NLP—0
SUGAR: Spherical Ultrafast Graph Attention Framework for Cortical Surface Registration—0
Summarizing Patients Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models—0
Summarizing Patients’ Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models—0
Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation—0
Superposition as Data Augmentation using LSTM and HMM in Small Training Sets—0
Supervised Contrastive Learning Approach for Contextual Ranking—0
Supervised Contrastive Learning for Accented Speech Recognition—0
Supervised Contrastive Learning for Ordinal Engagement Measurement—0
Supervised Contrastive Learning on Blended Images for Long-tailed Recognition—0
Supervised Contrastive Learning with Tree-Structured Parzen Estimator Bayesian Optimization for Imbalanced Tabular Data—0
Supervised Graph Contrastive Learning for Gene Regulatory Network—0
Supervised neural machine translation based on data augmentation and improved training \& inference process—0
SurfaceAug: Closing the Gap in Multimodal Ground Truth Sampling—0
Surface Defect Classification in Real-Time Using Convolutional Neural Networks—0
Surface Vision Transformers: Flexible Attention-Based Modelling of Biomedical Surfaces—0
SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning—0
Surgical Mask Detection with Convolutional Neural Networks and Data Augmentations on Spectrograms—0
Su-RoBERTa: A Semi-supervised Approach to Predicting Suicide Risk through Social Media using Base Language Models—0
Surprisingly Fragile: Assessing and Addressing Prompt Instability in Multimodal Foundation Models—0
Survey on Monocular Metric Depth Estimation—0
SViTT-Ego: A Sparse Video-Text Transformer for Egocentric Video—0
Swapping Semantic Contents for Mixing Images—0
Swin Transformer for Robust CGI Images Detection: Intra- and Inter-Dataset Analysis across Multiple Color Spaces—0
Switchable Lightweight Anti-symmetric Processing (SLAP) with CNN Outspeeds Data Augmentation by Smaller Sample -- Application in Gomoku Reinforcement Learning—0
Show:102550
← PrevPage 90 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