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 5151–5200 of 8378 papers

TitleStatusHype
Test Time Transform Prediction for Open Set Histopathological Image RecognitionCode0
Test-time image-to-image translation ensembling improves out-of-distribution generalization in histopathology—0
A ResNet attention model for classifying mosquitoes from wing‑beating soundsCode0
Transfer Learning for Robust Low-Resource Children's Speech ASR with Transformers and Source-Filter Warping—0
Hybrid Facial Expression Recognition (FER2013) Model for Real-Time Emotion Classification and Prediction—0
Data Augmentation vs. Equivariant Networks: A Theory of Generalization on Dynamics Forecasting—0
UI Layers Merger: Merging UI layers via Visual Learning and Boundary PriorCode0
Explainable Global Error Weighted on Feature Importance: The xGEWFI metric to evaluate the error of data imputation and data augmentation—0
DU-Net based Unsupervised Contrastive Learning for Cancer Segmentation in Histology Images—0
VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix—0
A Spatio-Temporal Neural Network Forecasting Approach for Emulation of Firefront Models—0
Small Object Detection via Pixel Level Balancing With Applications to Blood Cell DetectionCode0
Noisy Learning for Neural ODEs Acts as a Robustness Locus Widening—0
AI Enlightens Wireless Communication: A Transformer Backbone for CSI Feedback—0
PreCogIIITH at HinglishEval : Leveraging Code-Mixing Metrics & Language Model Embeddings To Estimate Code-Mix QualityCode0
iBoot: Image-bootstrapped Self-Supervised Video Representation Learning—0
Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?—0
Longitudinal detection of new MS lesions using Deep Learning—0
A Projection-Based K-space Transformer Network for Undersampled Radial MRI Reconstruction with Limited Training Subjects—0
BaIT: Barometer for Information Trustworthiness—0
Contrastive Learning as Goal-Conditioned Reinforcement Learning—0
Exploiting Cross-domain And Cross-Lingual Ultrasound Tongue Imaging Features For Elderly And Dysarthric Speech Recognition—0
Physically-admissible polarimetric data augmentation for road-scene analysis—0
A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classification Tasks—0
Toward Student-Oriented Teacher Network Training For Knowledge Distillation—0
Low-complexity deep learning frameworks for acoustic scene classification—0
Mapping fNIRS to fMRI with Neural Data Augmentation and Machine Learning Models—0
Virtual embeddings and self-consistency for self-supervised learning—0
2nd Place Solution for ICCV 2021 VIPriors Image Classification Challenge: An Attract-and-Repulse Learning Approach—0
The YiTrans End-to-End Speech Translation System for IWSLT 2022 Offline Shared Task—0
Modeling Generalized Specialist Approach To Train Quality Resilient Snapshot EnsembleCode0
Data Augmentation for Intent Classification—0
GAN based Data Augmentation to Resolve Class Imbalance—0
Is Self-Supervised Learning More Robust Than Supervised Learning?—0
Lost in Transmission: On the Impact of Networking Corruptions on Video Machine Learning Models—0
Heterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement—0
Memory Classifiers: Two-stage Classification for Robustness in Machine Learning—0
Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields—0
BSM loss: A superior way in modeling aleatory uncertainty of fine_grained classification—0
Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition—0
On gradient descent training under data augmentation with on-line noisy copies—0
Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical SubstitutionCode0
Marvolo: Programmatic Data Augmentation for Practical ML-Driven Malware Detection—0
An efficient semi-supervised quality control system trained using physics-based MRI-artefact generators and adversarial training—0
PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System—0
Global Mixup: Eliminating Ambiguity with Clustering—0
Mixed Graph Contrastive Network for Semi-Supervised Node Classification—0
Stacked unsupervised learning with a network architecture found by supervised meta-learning—0
AugLoss: A Robust Augmentation-based Fine Tuning Methodology—0
Adversarial Unlearning: Reducing Confidence Along Adversarial Directions—0
Show:102550
← PrevPage 104 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