SOTAVerified

Contrastive Learning

Contrastive Learning is a deep learning technique for unsupervised representation learning. The goal is to learn a representation of data such that similar instances are close together in the representation space, while dissimilar instances are far apart.

It has been shown to be effective in various computer vision and natural language processing tasks, including image retrieval, zero-shot learning, and cross-modal retrieval. In these tasks, the learned representations can be used as features for downstream tasks such as classification and clustering.

(Image credit: Schroff et al. 2015)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1551–1600 of 6661 papers

TitleStatusHype
Contrastive Learning of User Behavior Sequence for Context-Aware Document RankingCode1
Self-Supervised Graph Co-Training for Session-based RecommendationCode1
Generative and Contrastive Self-Supervised Learning for Graph Anomaly DetectionCode1
Unsupervised Local Discrimination for Medical ImagesCode1
Feature Stylization and Domain-aware Contrastive Learning for Domain GeneralizationCode1
Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text ModelsCode1
Graph Contrastive Learning for Anomaly DetectionCode1
RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object DetectionCode1
Scene Designer: a Unified Model for Scene Search and Synthesis from SketchCode1
Contrastive Self-supervised Sequential Recommendation with Robust AugmentationCode1
Learning to Cut by Watching MoviesCode1
Skeleton-Contrastive 3D Action Representation LearningCode1
Improving Contrastive Learning by Visualizing Feature TransformationCode1
Video Contrastive Learning with Global ContextCode1
Enhancing Self-supervised Video Representation Learning via Multi-level Feature OptimizationCode1
Improving Music Performance Assessment with Contrastive LearningCode1
Object-aware Contrastive Learning for Debiased Scene RepresentationCode1
Synth-by-Reg (SbR): Contrastive learning for synthesis-based registration of paired imagesCode1
Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labelsCode1
Self-Supervised Learning for Fine-Grained Image ClassificationCode1
AASAE: Augmentation-Augmented Stochastic AutoencodersCode1
Parametric Contrastive LearningCode1
Boosting Few-Shot Classification with View-Learnable Contrastive LearningCode1
ReSSL: Relational Self-Supervised Learning with Weak AugmentationCode1
Token-Level Supervised Contrastive Learning for Punctuation RestorationCode1
OODformer: Out-Of-Distribution Detection TransformerCode1
Separating Skills and Concepts for Novel Visual Question AnsweringCode1
Lesion-based Contrastive Learning for Diabetic Retinopathy Grading from Fundus ImagesCode1
Self-supervised Representation Learning Framework for Remote Physiological Measurement Using Spatiotemporal Augmentation LossCode1
More Robust Dense Retrieval with Contrastive Dual LearningCode1
Anatomy-Constrained Contrastive Learning for Synthetic Segmentation without Ground-truthCode1
Contrastive Learning for Cold-Start RecommendationCode1
A Hierarchical Dual Model of Environment- and Place-Specific Utility for Visual Place RecognitionCode1
Contrastive Multimodal Fusion with TupleInfoNCECode1
Improving Text-to-Image Synthesis Using Contrastive LearningCode1
Distance-based Hyperspherical Classification for Multi-source Open-Set Domain AdaptationCode1
Bag of Instances Aggregation Boosts Self-supervised DistillationCode1
Simpler, Faster, Stronger: Breaking The log-K Curse On Contrastive Learners With FlatNCECode1
CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language UnderstandingCode1
OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled DataCode1
Self-Contrastive Learning: Single-viewed Supervised Contrastive Framework using Sub-networkCode1
Co^2L: Contrastive Continual LearningCode1
UMIC: An Unreferenced Metric for Image Captioning via Contrastive LearningCode1
Time-Series Representation Learning via Temporal and Contextual ContrastingCode1
Winning the CVPR'2021 Kinetics-GEBD Challenge: Contrastive Learning ApproachCode1
VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive LearningCode1
Can contrastive learning avoid shortcut solutions?Code1
Multi-level Feature Learning for Contrastive Multi-view ClusteringCode1
Underwater Image Restoration via Contrastive Learning and a Real-world DatasetCode1
Neighborhood Contrastive Learning for Novel Class DiscoveryCode1
Show:102550
← PrevPage 32 of 134Next →
All datasetsimagenet-1k10,000 People - Human Pose Recognition DataCIFAR-10STL-10

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6—Unverified
2ResNet50ImageNet Top-1 Accuracy73—Unverified
3ResNet50ImageNet Top-1 Accuracy71.1—Unverified
4ResNet50ImageNet Top-1 Accuracy69.3—Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6—Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8—Unverified
7ResNet50ImageNet Top-1 Accuracy63.6—Unverified
8ResNet50ImageNet Top-1 Accuracy61.5—Unverified
9ResNet50ImageNet Top-1 Accuracy61.5—Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3—Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1—Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77—Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55—Unverified