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 2326–2350 of 6661 papers

TitleStatusHype
Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be BetterCode0
GaussianStyle: Gaussian Head Avatar via StyleGANCode0
iMove: Exploring Bio-impedance Sensing for Fitness Activity Recognition—0
Graph Contrastive Learning with Cohesive Subgraph AwarenessCode1
Towards Personalized Privacy: User-Governed Data Contribution for Federated Recommendation—0
Optimizing contrastive learning for cortical folding pattern detectionCode0
Graph Multi-Similarity Learning for Molecular Property Prediction—0
Rank Supervised Contrastive Learning for Time Series Classification—0
Learning Label Hierarchy with Supervised Contrastive LearningCode0
Episodic-free Task Selection for Few-shot Learning—0
All Beings Are Equal in Open Set Recognition—0
Distillation Enhanced Time Series Forecasting Network with Momentum Contrastive LearningCode0
Self-Supervised Representation Learning for Nerve Fiber Distribution Patterns in 3D-PLI—0
Detection and Recovery Against Deep Neural Network Fault Injection Attacks Based on Contrastive Learning—0
Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive LearningCode0
MolPLA: A Molecular Pretraining Framework for Learning Cores, R-Groups and their Linker JointsCode0
Supervised Contrastive Learning based Dual-Mixer Model for Remaining Useful Life PredictionCode1
ConFit: Improving Resume-Job Matching using Data Augmentation and Contrastive Learning—0
MLEM: Generative and Contrastive Learning as Distinct Modalities for Event SequencesCode0
PICL: Physics Informed Contrastive Learning for Partial Differential EquationsCode0
GPS: Graph Contrastive Learning via Multi-scale Augmented Views from Adversarial Pooling—0
Regressing Transformers for Data-efficient Visual Place Recognition—0
RecDCL: Dual Contrastive Learning for RecommendationCode1
Contrastive Learning and Mixture of Experts Enables Precise Vector EmbeddingsCode1
LegalDuet: Learning Fine-grained Representations for Legal Judgment Prediction via a Dual-View Contrastive LearningCode1
Show:102550
← PrevPage 94 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