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 1051–1100 of 8378 papers

TitleStatusHype
CVAE-GAN: Fine-Grained Image Generation through Asymmetric TrainingCode1
Continual Few-shot Relation Learning via Embedding Space Regularization and Data AugmentationCode1
Automated segmentation and morphological characterization of placental histology images based on a single labeled imageCode1
Continuous Copy-Paste for One-Stage Multi-Object Tracking and SegmentationCode1
Context Decoupling Augmentation for Weakly Supervised Semantic SegmentationCode1
Back to Basics: A Simple Recipe for Improving Out-of-Domain Retrieval in Dense EncodersCode1
Contrastive Learning for Knowledge TracingCode1
Contrastive Learning for Many-to-many Multilingual Neural Machine TranslationCode1
Addressing the confounds of accompaniments in singer identificationCode1
Contrastive Learning of User Behavior Sequence for Context-Aware Document RankingCode1
Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical ReasoningCode1
Contrastive Neural Processes for Self-Supervised LearningCode1
A class-weighted supervised contrastive learning long-tailed bearing fault diagnosis approach using quadratic neural networkCode1
Control, Generate, Augment: A Scalable Framework for Multi-Attribute Text GenerationCode1
Analysis of skin lesion images with deep learningCode1
Controllable Data Augmentation Through Deep RelightingCode1
Context-Aware Deep Learning for Multi Modal Depression DetectionCode1
Convex Combination Consistency between Neighbors for Weakly-supervised Action LocalizationCode1
PIGNet2: A Versatile Deep Learning-based Protein-Ligand Interaction Prediction Model for Binding Affinity Scoring and Virtual ScreeningCode1
Convolutional neural networks with low-rank regularizationCode1
ACLM: A Selective-Denoising based Generative Data Augmentation Approach for Low-Resource Complex NERCode1
A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution RobustnessCode1
Automatic Data Augmentation for Generalization in Deep Reinforcement LearningCode1
Automatic Data Augmentation for Generalization in Reinforcement LearningCode1
Automatic Data Augmentation for 3D Medical Image SegmentationCode1
Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language NavigationCode1
Counterfactual Data Augmentation using Locally Factored DynamicsCode1
Learning from Counterfactual Links for Link PredictionCode1
Analyzing Overfitting under Class Imbalance in Neural Networks for Image SegmentationCode1
Background-Mixed Augmentation for Weakly Supervised Change DetectionCode1
Cross-Domain Adaptive Teacher for Object DetectionCode1
Cross-head mutual Mean-Teaching for semi-supervised medical image segmentationCode1
Cross-modulated Few-shot Image Generation for Colorectal Tissue ClassificationCode1
Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text GuidanceCode1
CUDA: Curriculum of Data Augmentation for Long-Tailed RecognitionCode1
CultureLLM: Incorporating Cultural Differences into Large Language ModelsCode1
Bayesian Adversarial Human Motion SynthesisCode1
D3A-TS: Denoising-Driven Data Augmentation in Time SeriesCode1
An Analysis of Simple Data Augmentation for Named Entity RecognitionCode1
DADA: Differentiable Automatic Data AugmentationCode1
DALE: Generative Data Augmentation for Low-Resource Legal NLPCode1
Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentationCode1
Data Augmentation Alone Can Improve Adversarial TrainingCode1
Contextual Similarity Aggregation with Self-attention for Visual Re-rankingCode1
Data Augmentation Based Malware Detection using Convolutional Neural NetworksCode1
Data Augmentation for Abstractive Query-Focused Multi-Document SummarizationCode1
Data Augmentation for Deep Candlestick LearnerCode1
BAGAN: Data Augmentation with Balancing GANCode1
Bag of Tricks for Long-Tailed Visual Recognition with Deep Convolutional Neural NetworksCode1
Continuous Language Generative FlowCode1
Show:102550
← PrevPage 22 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