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 5651–5700 of 8378 papers

TitleStatusHype
AquaFuse: Waterbody Fusion for Physics Guided View Synthesis of Underwater Scenes—0
A Quality-Centric Framework for Generic Deepfake Detection—0
A quantifiable testing of global translational invariance in Convolutional and Capsule Networks—0
AraBench: Benchmarking Dialectal Arabic-English Machine Translation—0
Arabic dialect identification: An Arabic-BERT model with data augmentation and ensembling strategy—0
Arabic Tweet Act: A Weighted Ensemble Pre-Trained Transformer Model for Classifying Arabic Speech Acts on Twitter—0
ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations—0
Mixture Data for Training Cannot Ensure Out-of-distribution Generalization—0
A Recipe for Efficient SBIR Models: Combining Relative Triplet Loss with Batch Normalization and Knowledge Distillation—0
Are conditional GANs explicitly conditional?—0
Are Current Task-oriented Dialogue Systems Able to Satisfy Impolite Users?—0
A Recurrent YOLOv8-based framework for Event-Based Object Detection—0
Are Deep Learning Models Robust to Partial Object Occlusion in Visual Recognition Tasks?—0
Are labels informative in semi-supervised learning? -- Estimating and leveraging the missing-data mechanism—0
A Relational Model for One-Shot Classification—0
Are NeRFs ready for autonomous driving? Towards closing the real-to-simulation gap—0
A Review of Image Retrieval Techniques: Data Augmentation and Adversarial Learning Approaches—0
Classification of White Blood Cells Using Machine and Deep Learning Models: A Systematic Review—0
A Review on Generative Adversarial Networks for Data Augmentation in Person Re-Identification Systems—0
Are you wearing a mask? Improving mask detection from speech using augmentation by cycle-consistent GANs—0
A Rigorous Evaluation of Real-World Distribution Shifts—0
Arithmetic Reasoning with LLM: Prolog Generation & Permutation—0
ARMADA: Attribute-Based Multimodal Data Augmentation—0
ARMOR: Shielding Unlearnable Examples against Data Augmentation—0
A Robust and Scalable Attention Guided Deep Learning Framework for Movement Quality Assessment—0
A robust assessment for invariant representations—0
A Robust Attack: Displacement Backdoor Attack—0
A Robust Ensemble Model for Patasitic Egg Detection and Classification—0
A Robust Illumination-Invariant Camera System for Agricultural Applications—0
A Robust Pose Transformational GAN for Pose Guided Person Image Synthesis—0
ARPA: A Novel Hybrid Model for Advancing Visual Word Disambiguation Using Large Language Models and Transformers—0
Artificial Intelligence-Enhanced Couinaud Segmentation for Precision Liver Cancer Therapy—0
ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition—0
A scoping review of transfer learning research on medical image analysis using ImageNet—0
A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs—0
A Self-Training Method for Semi-Supervised GANs—0
A Semantic Alignment System for Multilingual Query-Product Retrieval—0
A Semantic Feature-Wise Transformation Relation Network for Automatic Short Answer Grading—0
A Semi-Supervised Approach with Error Reflection for Echocardiography Segmentation—0
AS-ES Learning: Towards Efficient CoT Learning in Small Models—0
AS-GCL: Asymmetric Spectral Augmentation on Graph Contrastive Learning—0
A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness—0
A Simple Background Augmentation Method for Object Detection with Diffusion Model—0
Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?—0
N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking—0
A Simple Data Augmentation for Feature Distribution Skewed Federated Learning—0
A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Image—0
A Simple Feature Augmentation for Domain Generalization—0
A Simple Strategy to Provable Invariance via Orbit Mapping—0
Supervised Graph Contrastive Learning for Few-shot Node Classification—0
Show:102550
← PrevPage 114 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