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 3376–3400 of 6661 papers

TitleStatusHype
Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transport—0
Unsupervised Cross-Domain Rumor Detection with Contrastive Learning and Cross-Attention—0
Unsupervised dense retrieval with conterfactual contrastive learning—0
Unsupervised Deraining: Where Asymmetric Contrastive Learning Meets Self-similarity—0
Unsupervised Detection of Fraudulent Transactions in E-commerce Using Contrastive Learning—0
Unsupervised Document Embedding via Contrastive Augmentation—0
Unsupervised Domain Adaptation for COVID-19 Information Service with Contrastive Adversarial Domain Mixup—0
Unsupervised Domain Adaptation for Training Event-Based Networks Using Contrastive Learning and Uncorrelated Conditioning—0
Unsupervised domain adaptation via coarse-to-fine feature alignment method using contrastive learning—0
Unsupervised Domain Adaptation with Contrastive Learning for Cross-domain Chinese NER—0
Unsupervised Domain Adaptation with Contrastive Learning for OCT Segmentation—0
Unsupervised Domain Adaptive Person Re-id with Local-enhance and Prototype Dictionary Learning—0
Unsupervised Driving Event Discovery Based on Vehicle CAN-data—0
Unsupervised Feature Clustering Improves Contrastive Representation Learning for Medical Image Segmentation—0
Unsupervised Federated Optimization at the Edge: D2D-Enabled Learning without Labels—0
Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation—0
Unsupervised Flood Detection on SAR Time Series—0
Unsupervised Gait Recognition with Selective Fusion—0
Unsupervised Gaze-aware Contrastive Learning with Subject-specific Condition—0
Unsupervised Generative Feature Transformation via Graph Contrastive Pre-training and Multi-objective Fine-tuning—0
ImitationNet: Unsupervised Human-to-Robot Motion Retargeting via Shared Latent Space—0
Unsupervised learning based object detection using Contrastive Learning—0
Unsupervised Learning for Human Sensing Using Radio Signals—0
Unsupervised Learning of Dense Visual Representations—0
Unsupervised learning of features and object boundaries from local prediction—0
Show:102550
← PrevPage 136 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