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 5276–5300 of 6661 papers

TitleStatusHype
Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations—0
Contrastive Meta Learning with Behavior Multiplicity for RecommendationCode1
Eliciting Structural and Semantic Global Knowledge in Unsupervised Graph Contrastive LearningCode1
Augment with Care: Contrastive Learning for Combinatorial ProblemsCode0
Self-Supervised Representation Learning via Latent Graph Prediction—0
Misinformation Detection in Social Media Video Posts—0
Self-Supervised Class-Cognizant Few-Shot ClassificationCode0
Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learning—0
Neighborhood Contrastive Learning for Scientific Document Representations with Citation EmbeddingsCode1
Adversarial Graph Contrastive Learning with Information RegularizationCode0
A Generic Self-Supervised Framework of Learning Invariant Discriminative Features—0
Learning Weakly-Supervised Contrastive RepresentationsCode1
Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training BenchmarkCode0
Synthetic Data Can Also Teach: Synthesizing Effective Data for Unsupervised Visual Representation Learning—0
Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Search—0
Learning long-term music representations via hierarchical contextual constraints—0
Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive LearningCode1
Geometric Graph Representation Learning via Maximizing Rate Reduction—0
What Makes Good Contrastive Learning on Small-Scale Wearable-based Tasks?Code1
Metadata-Induced Contrastive Learning for Zero-Shot Multi-Label Text ClassificationCode1
Conditional Contrastive Learning with KernelCode1
SuperCon: Supervised Contrastive Learning for Imbalanced Skin Lesion Classification—0
From Unsupervised to Few-shot Graph Anomaly Detection: A Multi-scale Contrastive Learning Approach—0
Using Navigational Information to Learn Visual Representations—0
Energy-Based Contrastive Learning of Visual RepresentationsCode1
Show:102550
← PrevPage 212 of 267Next →
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