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 301–350 of 6661 papers

TitleStatusHype
Replication: Contrastive Learning and Data Augmentation in Traffic Classification Using a Flowpic Input RepresentationCode1
Boosting Few-Shot Classification with View-Learnable Contrastive LearningCode1
Contrastive Learning and Mixture of Experts Enables Precise Vector EmbeddingsCode1
Blind Localization and Clustering of Anomalies in TexturesCode1
Black Box Few-Shot Adaptation for Vision-Language modelsCode1
Boosting Contrastive Self-Supervised Learning with False Negative CancellationCode1
Contrastive Learning-Based Audio to Lyrics Alignment for Multiple LanguagesCode1
Boosting Semi-Supervised Semantic Segmentation with Probabilistic RepresentationsCode1
A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment AnalysisCode1
Contrastive Label Disambiguation for Partial Label LearningCode1
BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and MappingCode1
Bridging Spectral-wise and Multi-spectral Depth Estimation via Geometry-guided Contrastive LearningCode1
Black-Box Attack against GAN-Generated Image Detector with Contrastive PerturbationCode1
Contrastive Laplacian EigenmapsCode1
A Unified Generative Framework for Realistic Lidar Simulation in Autonomous Driving SystemsCode1
Biomedical Entity Linking with Contrastive Context MatchingCode1
Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World AttacksCode1
Contrastive Fine-grained Class Clustering via Generative Adversarial NetworksCode1
3D Interaction Geometric Pre-training for Molecular Relational LearningCode1
Adversarial Self-Supervised Contrastive LearningCode1
BIOSCAN-5M: A Multimodal Dataset for Insect BiodiversityCode1
Contrastive Grouping with Transformer for Referring Image SegmentationCode1
CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at ScaleCode1
Contrastive Denoising Score for Text-guided Latent Diffusion Image EditingCode1
Normality Learning-based Graph Anomaly Detection via Multi-Scale Contrastive LearningCode1
3D Infomax improves GNNs for Molecular Property PredictionCode1
Contrastive Embeddings for Neural ArchitecturesCode1
Contrastive Identity-Aware Learning for Multi-Agent Value DecompositionCode1
Contrastive Learning for Cold-Start RecommendationCode1
Contrastive Learning for Unsupervised Domain Adaptation of Time SeriesCode1
Contrastive Mean Teacher for Domain Adaptive Object DetectorsCode1
Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure LearningCode1
A Comparative Study of Pre-trained Encoders for Low-Resource Named Entity RecognitionCode1
Contrastive Code Representation LearningCode1
Contrastive Bayesian Analysis for Deep Metric LearningCode1
3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised LearningCode1
Contrastive ClusteringCode1
Contrastive Collaborative Filtering for Cold-Start Item RecommendationCode1
Adversarial Graph Augmentation to Improve Graph Contrastive LearningCode1
3D Human Pose, Shape and Texture from Low-Resolution Images and VideosCode1
Big Self-Supervised Models Advance Medical Image ClassificationCode1
A Closer Look at Self-Supervised Lightweight Vision TransformersCode1
Adversarial Examples Are Not Real FeaturesCode1
Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class DiscoveryCode1
Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation DistillationCode1
Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-SeriesCode1
Adversarial Contrastive Learning via Asymmetric InfoNCECode1
Adversarial Contrastive Learning for Evidence-aware Fake News Detection with Graph Neural NetworksCode1
3D Human Action Representation Learning via Cross-View Consistency PursuitCode1
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional UnderstandingCode1
Show:102550
← PrevPage 7 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