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 2251–2275 of 6661 papers

TitleStatusHype
Learning the Unlearned: Mitigating Feature Suppression in Contrastive LearningCode1
HU at SemEval-2024 Task 8A: Can Contrastive Learning Learn Embeddings to Detect Machine-Generated Text?Code0
Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative FilteringCode2
PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay ReconstructionCode0
A Temporally Disentangled Contrastive Diffusion Model for Spatiotemporal Imputation—0
Continuous Multi-Task Pre-training for Malicious URL Detection and Webpage ClassificationCode1
Assessing News Thumbnail Representativeness: Counterfactual text can enhance the cross-modal matching abilityCode0
Pretext Training Algorithms for Event Sequence Data—0
Fusion of Diffusion Weighted MRI and Clinical Data for Predicting Functional Outcome after Acute Ischemic Stroke with Deep Contrastive Learning—0
A Condensed Transition Graph Framework for Zero-shot Link Prediction with Large Language Models—0
Adversarial Curriculum Graph Contrastive Learning with Pair-wise Augmentation—0
Parametric Augmentation for Time Series Contrastive LearningCode1
Training Class-Imbalanced Diffusion Model Via Overlap OptimizationCode0
Dynamic Patch-aware Enrichment Transformer for Occluded Person Re-Identification—0
Multiview Contrastive Learning for Unsupervised Domain Adaptation in Brain–Computer Interfaces—0
MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained RepresentationsCode1
Sequential Recommendation on Temporal Proximities with Contrastive Learning and Self-Attention—0
MM-Point: Multi-View Information-Enhanced Multi-Modal Self-Supervised 3D Point Cloud UnderstandingCode1
f-MICL: Understanding and Generalizing InfoNCE-based Contrastive Learning—0
Low-Rank Graph Contrastive Learning for Node Classification—0
Integrating ChatGPT into Secure Hospital Networks: A Case Study on Improving Radiology Report Analysis—0
Disambiguated Node Classification with Graph Neural NetworksCode0
AMEND: A Mixture of Experts Framework for Long-tailed Trajectory Prediction—0
DNABERT-S: Pioneering Species Differentiation with Species-Aware DNA EmbeddingsCode2
Modeling Balanced Explicit and Implicit Relations with Contrastive Learning for Knowledge Concept Recommendation in MOOCs—0
Show:102550
← PrevPage 91 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