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 3226–3250 of 6661 papers

TitleStatusHype
mCLIP: Multilingual CLIP via Cross-lingual TransferCode1
Hate Speech Detection via Dual Contrastive Learning—0
Towards Cross-Table Masked Pretraining for Web Data MiningCode1
Improving Factuality of Abstractive Summarization via Contrastive Reward Learning—0
Joint Salient Object Detection and Camouflaged Object Detection via Uncertainty-aware Learning—0
Graph Contrastive Learning with Multi-Objective for Personalized Product Retrieval in Taobao Search—0
Generalizing Graph ODE for Learning Complex System Dynamics across Environments—0
Weakly-supervised positional contrastive learning: application to cirrhosis classificationCode1
CognitiveNet: Enriching Foundation Models with Emotions and Awareness—0
DEDUCE: Multi-head attention decoupled contrastive learning to discover cancer subtypes based on multi-omics dataCode0
FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?—0
ECL: Class-Enhancement Contrastive Learning for Long-tailed Skin Lesion ClassificationCode1
End-to-End Supervised Multilabel Contrastive LearningCode0
Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive LearningCode1
AdaptiveRec: Adaptively Construct Pairs for Contrastive Learning in Sequential Recommendation—0
Weakly-supervised Contrastive Learning for Unsupervised Object DiscoveryCode0
Polybot: Training One Policy Across Robots While Embracing Variability—0
Focused Transformer: Contrastive Training for Context ScalingCode3
Knowledge Graph Self-Supervised Rationalization for RecommendationCode1
Semi-supervised Domain Adaptive Medical Image Segmentation through Consistency Regularized Disentangled Contrastive LearningCode1
Multi-Similarity Contrastive Learning—0
Contrast Is All You Need—0
Fisher-Weighted Merge of Contrastive Learning Models in Sequential Recommendation—0
STS-CCL: Spatial-Temporal Synchronous Contextual Contrastive Learning for Urban Traffic Forecasting—0
Graph Contrastive Topic ModelCode0
Show:102550
← PrevPage 130 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