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 4701–4750 of 8378 papers

TitleStatusHype
Restoration of Hand-Drawn Architectural Drawings Using Latent Space Mapping With Degradation Generator—0
Restrained Generative Adversarial Network against Overfitting in Numeric Data Augmentation—0
Revisiting and Advancing Adversarial Training Through A Simple Baseline—0
Rethinking and Designing a High-performing Automatic License Plate Recognition Approach—0
Rethinking Cost-sensitive Classification in Deep Learning via Adversarial Data Augmentation—0
On Counterfactual Data Augmentation Under Confounding—0
Rethinking Curriculum Learning with Incremental Labels and Adaptive Compensation—0
Rethinking Data Augmentation in Text-to-text Paradigm—0
Rethinking Domain Generalization Baselines—0
Rethinking Few-Shot Medical Image Segmentation by SAM2: A Training-Free Framework with Augmentative Prompting and Dynamic Matching—0
Rethinking Range View Representation for LiDAR Segmentation—0
Rethinking Samples Selection for Contrastive Learning: Mining of Potential Samples—0
Rethinking Soft Label in Label Distribution Learning Perspective—0
Rethinking Sparse Lexical Representations for Image Retrieval in the Age of Rising Multi-Modal Large Language Models—0
Rethinking the Defocus Blur Detection Problem and A Real-Time Deep DBD Model—0
Digging Errors in NMT: Evaluating and Understanding Model Errors from Partial Hypothesis Space—0
Rethinking the impact of noisy labels in graph classification: A utility and privacy perspective—0
Rethinking Ultrasound Augmentation: A Physics-Inspired Approach—0
Rethink the Effectiveness of Text Data Augmentation: An Empirical Analysis—0
Retinal Image Segmentation with Small Datasets—0
Re-translation versus Streaming for Simultaneous Translation—0
Retrieval-Augmented Data Augmentation for Low-Resource Domain Tasks—0
Retrieval Augmented Image Harmonization—0
Retrieval Based Response Letter Generation For a Customer Care Setting—0
Retrieval Data Augmentation Informed by Downstream Question Answering Performance—0
Retrieval Data Augmentation Informed by Downstream Question Answering Performance—0
Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies—0
Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies—0
Retrieval-guided Counterfactual Generation for QA—0
Retrieval-guided Counterfactual Generation for QA—0
Retrieve Synonymous keywords for Frequent Queries in Sponsored Search in a Data Augmentation Way—0
Retro-Actions: Learning 'Close' by Time-Reversing 'Open' Videos—0
Retrosynthesis prediction enhanced by in-silico reaction data augmentation—0
Revealing Lung Affections from CTs. A Comparative Analysis of Various Deep Learning Approaches for Dealing with Volumetric Data—0
Revealing the Two Sides of Data Augmentation: An Asymmetric Distillation-based Win-Win Solution for Open-Set Recognition—0
Reverse Thinking Makes LLMs Stronger Reasoners—0
Revisiting Contextual Toxicity Detection in Conversations—0
Revisiting Data Augmentation for Rotational Invariance in Convolutional Neural Networks—0
Revisiting data augmentation for subspace clustering—0
Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Study—0
Revisiting Deep Semi-supervised Learning: An Empirical Distribution Alignment Framework and Its Generalization Bound—0
Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack—0
Revisiting In-Context Learning with Long Context Language Models—0
Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors—0
Revisiting Meta-Learning as Supervised Learning—0
Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in Surface Electromyographic Signal Analysis—0
Revisiting Optical Flow Estimation in 360 Videos—0
Revolutionizing Communication with Deep Learning and XAI for Enhanced Arabic Sign Language Recognition—0
Revolutionizing Wildfire Detection with Convolutional Neural Networks: A VGG16 Model Approach—0
Riesz networks: scale invariant neural networks in a single forward pass—0
Show:102550
← PrevPage 95 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