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 8051–8100 of 8378 papers

TitleStatusHype
Combining Pyramid Pooling and Attention Mechanism for Pelvic MR Image Semantic Segmentaion—0
Multistage Adversarial Losses for Pose-Based Human Image Synthesis—0
MIT-MEDG at SemEval-2018 Task 7: Semantic Relation Classification via Convolution Neural Network—0
Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion CompensationCode0
Self-Training for Jointly Learning to Ask and Answer Questions—0
Pose-Guided Photorealistic Face Rotation—0
Using Paraphrasing and Memory-Augmented Models to Combat Data Sparsity in Question Interpretation with a Virtual Patient Dialogue System—0
MONET: Multiview Semi-supervised Keypoint Detection via Epipolar DivergenceCode0
Long-time predictive modeling of nonlinear dynamical systems using neural networks—0
Accurate pedestrian localization in overhead depth images via Height-Augmented HOG—0
Generalizing to Unseen Domains via Adversarial Data AugmentationCode0
Learning Data Augmentation for Brain Tumor Segmentation with Coarse-to-Fine Generative Adversarial Networks—0
Improved Mixed-Example Data AugmentationCode0
Capturing Variabilities from Computed Tomography Images with Generative Adversarial Networks—0
Transductive Label Augmentation for Improved Deep Network Learning—0
Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM—0
Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation—0
Input and Weight Space Smoothing for Semi-supervised Learning—0
Enriched Long-term Recurrent Convolutional Network for Facial Micro-Expression RecognitionCode0
Abstractive Text Classification Using Sequence-to-convolution Neural NetworksCode0
Generating High-Quality Surface Realizations Using Data Augmentation and Factored Sequence Models—0
Counterexample-Guided Data AugmentationCode0
Resisting Large Data Variations via Introspective Transformation Network—0
Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification—0
Adversarial Training for Patient-Independent Feature Learning with IVOCT Data for Plaque Classification—0
Contextual Augmentation: Data Augmentation by Words with Paradigmatic RelationsCode0
Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learning—0
Stingray Detection of Aerial Images Using Augmented Training Images Generated by A Conditional Generative Model—0
Learning Domain-Sensitive and Sentiment-Aware Word Embeddings—0
Image Ordinal Classification and Understanding: Grid Dropout with Masking Label—0
Augmenting Image Question Answering Dataset by Exploiting Image Captions—0
Simulating ASR errors for training SLU systems—0
Deep JSLC: A Multimodal Corpus Collection for Data-driven Generation of Japanese Sign Language Expressions—0
Evaluation of Feature-Space Speaker Adaptation for End-to-End Acoustic Models—0
Handling Rare Word Problem using Synthetic Training Data for Sinhala and Tamil Neural Machine Translation—0
Generalizing Across Domains via Cross-Gradient TrainingCode0
Simulating dysarthric speech for training data augmentation in clinical speech applications—0
Spatiotemporal Learning of Dynamic Gestures from 3D Point Cloud Data—0
Automatic speech recognition for launch control center communication using recurrent neural networks with data augmentation and custom language model—0
Learning to See the Invisible: End-to-End Trainable Amodal Instance SegmentationCode0
MVTec D2S: Densely Segmented Supermarket Dataset—0
Word Embedding Perturbation for Sentence ClassificationCode0
Learning to Refine Human Pose Estimation—0
Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages—0
Robust Machine Comprehension Models via Adversarial Training—0
Building robust prediction models for defective sensor data using Artificial Neural Networks—0
Transcribing Lyrics From Commercial Song Audio: The First Step Towards Singing Content Processing—0
3D G-CNNs for Pulmonary Nodule Detection—0
Real-world plant species identification based on deep convolutional neural networks and visual attention—0
E-commerce Anomaly Detection: A Bayesian Semi-Supervised Tensor Decomposition Approach using Natural Gradients—0
Show:102550
← PrevPage 162 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