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 2451–2500 of 6661 papers

TitleStatusHype
Contrastive Learning for Predicting Cancer Prognosis Using Gene Expression ValuesCode0
Contrastive Learning for OOD in Object detectionCode0
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One ClassifierCode0
Line Graph Contrastive Learning for Link PredictionCode0
Link Prediction with Non-Contrastive LearningCode0
Contrastive Learning for Online Semi-Supervised General Continual LearningCode0
Contrastive Learning for Object DetectionCode0
Lightweight Cross-Lingual Sentence Representation LearningCode0
Contrastive learning for natural language-based vehicle retrievalCode0
Contrastive Learning for Multi-Object Tracking with TransformersCode0
Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer FeaturesCode0
Contrastive Learning-based Chaining-Cluster for Multilingual Voice-Face AssociationCode0
Lexical Knowledge Internalization for Neural Dialog GenerationCode0
Leveraging Group Classification with Descending Soft Labeling for Deep Imbalanced RegressionCode0
Leveraging Contrastive Learning and Self-Training for Multimodal Emotion Recognition with Limited Labeled SamplesCode0
Leveraging Graph Structures to Detect Hallucinations in Large Language ModelsCode0
Contrastive Learning for Lane Detection via cross-similarityCode0
Less is More: Selective Reduction of CT Data for Self-Supervised Pre-Training of Deep Learning Models with Contrastive Learning Improves Downstream Classification PerformanceCode0
A Diffusion Weighted Graph Framework for New Intent DiscoveryCode0
Less is More: Multimodal Region Representation via Pairwise Inter-view LearningCode0
Contrastive Learning for Joint Normal Estimation and Point Cloud FilteringCode0
Length is a Curse and a Blessing for Document-level SemanticsCode0
Lesion-Aware Contrastive Representation Learning for Histopathology Whole Slide Images AnalysisCode0
Contrastive Learning for Inference in DialogueCode0
Cold-start Bundle Recommendation via Popularity-based Coalescence and Curriculum HeatingCode0
Contrastive Learning for Implicit Social Factors in Social Media Popularity PredictionCode0
Contrastive Learning for Image Registration in Visual Teach and Repeat NavigationCode0
Leave No One Behind: Online Self-Supervised Self-Distillation for Sequential RecommendationCode0
Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation SpaceCode0
Less Attention is More: Prompt Transformer for Generalized Category DiscoveryCode0
Leveraging Unlabeled Data for 3D Medical Image Segmentation through Self-Supervised Contrastive LearningCode0
Multi-View Action Recognition Using Contrastive LearningCode0
Learning to Locate Visual Answer in Video Corpus Using QuestionCode0
Anatomy-Aware Contrastive Representation Learning for Fetal UltrasoundCode0
Learning to Plan via Supervised Contrastive Learning and Strategic Interpolation: A Chess Case StudyCode0
Learning Transferable Pedestrian Representation from Multimodal Information SupervisionCode0
Learning Tree-Structured Composition of Data AugmentationCode0
3C: Confidence-Guided Clustering and Contrastive Learning for Unsupervised Person Re-IdentificationCode0
Learning the Simplicity of Scattering AmplitudesCode0
Bitext Mining for Low-Resource Languages via Contrastive LearningCode0
Learning Text Similarity with Siamese Recurrent NetworksCode0
Contrastive Learning for Character Detection in Ancient Greek PapyriCode0
Contrastive Learning for API Aspect AnalysisCode0
Contrastive Learning enhanced Author-Style Headline GenerationCode0
Addressing Order Sensitivity of In-Context Demonstration Examples in Causal Language ModelsCode0
Learning Semi-Supervised Medical Image Segmentation from Spatial RegistrationCode0
Learning Node Representations against PerturbationsCode0
Contrastive Learning-based Sentence Encoders Implicitly Weight Informative WordsCode0
Anatomical Conditioning for Contrastive Unpaired Image-to-Image Translation of Optical Coherence Tomography ImagesCode0
Learning Self-Supervised Representations for Label Efficient Cross-Domain Knowledge Transfer on Diabetic Retinopathy Fundus ImagesCode0
Show:102550
← PrevPage 50 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