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 4101–4125 of 6661 papers

TitleStatusHype
Contrastive Modules with Temporal Attention for Multi-Task Reinforcement LearningCode0
DyTSCL: Dynamic graph representation via tempo-structural contrastive learningCode0
Rethinking Samples Selection for Contrastive Learning: Mining of Potential Samples—0
On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval—0
Medi-CAT: Contrastive Adversarial Training for Medical Image Classification—0
Uncertainty-guided Boundary Learning for Imbalanced Social Event DetectionCode0
Improving Medical Visual Representations via Radiology Report Generation—0
Towards Generalized Multi-stage Clustering: Multi-view Self-distillation—0
A Unique Training Strategy to Enhance Language Models Capabilities for Health Mention Detection from Social Media Content—0
Retrofitting Light-weight Language Models for Emotions using Supervised Contrastive Learning—0
CHAIN: Exploring Global-Local Spatio-Temporal Information for Improved Self-Supervised Video Hashing—0
Adversarial Bootstrapped Question Representation Learning for Knowledge TracingCode0
ReConTab: Regularized Contrastive Representation Learning for Tabular Data—0
Alignment and Outer Shell Isotropy for Hyperbolic Graph Contrastive Learning—0
Image Prior and Posterior Conditional Probability Representation for Efficient Damage Assessment—0
PSP: Pre-Training and Structure Prompt Tuning for Graph Neural NetworksCode0
Boosting Multi-Speaker Expressive Speech Synthesis with Semi-supervised Contrastive Learning—0
IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery—0
DyExplainer: Explainable Dynamic Graph Neural Networks—0
Proposal-Contrastive Pretraining for Object Detection from Fewer Data—0
Model-enhanced Contrastive Reinforcement Learning for Sequential Recommendation—0
Length is a Curse and a Blessing for Document-level SemanticsCode0
A Diffusion Weighted Graph Framework for New Intent DiscoveryCode0
I^2MD: 3D Action Representation Learning with Inter- and Intra-modal Mutual Distillation—0
Unpaired MRI Super Resolution with Contrastive Learning—0
Show:102550
← PrevPage 165 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