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 2526–2550 of 6661 papers

TitleStatusHype
Learning the Simplicity of Scattering AmplitudesCode0
FedStyle: Style-Based Federated Learning Crowdsourcing Framework for Art CommissionsCode0
Contrastive learning-based computational histopathology predict differential expression of cancer driver genesCode0
FedSKC: Federated Learning with Non-IID Data via Structural Knowledge CollaborationCode0
FedSC: Federated Learning with Semantic-Aware CollaborationCode0
Learning Self-Supervised Representations for Label Efficient Cross-Domain Knowledge Transfer on Diabetic Retinopathy Fundus ImagesCode0
Learning Semi-Supervised Medical Image Segmentation from Spatial RegistrationCode0
Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient EncoderCode0
BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive LearningCode0
Learning Representations for Clustering via Partial Information Discrimination and Cross-Level InteractionCode0
Learning Node Representations against PerturbationsCode0
Learning Multimodal Volumetric Features for Large-Scale Neuron TracingCode0
Learning Label Hierarchy with Supervised Contrastive LearningCode0
Learning Invariance from Generated Variance for Unsupervised Person Re-identificationCode0
FedPCL-CDR: A Federated Prototype-based Contrastive Learning Framework for Privacy-Preserving Cross-domain RecommendationCode0
Learning Graph Augmentations to Learn Graph RepresentationsCode0
Learning Intra and Inter-Camera Invariance for Isolated Camera Supervised Person Re-identificationCode0
Learning Oculomotor Behaviors from ScanpathCode0
Learning Street View Representations with Spatiotemporal ContrastCode0
ACCIO: Table Understanding Enhanced via Contrastive Learning with AggregationsCode0
Bilingual Dual-Head Deep Model for Parkinson's Disease Detection from SpeechCode0
Contrastive Learning and Adversarial Disentanglement for Task-Oriented Semantic CommunicationsCode0
Analyzing Data-Centric Properties for Graph Contrastive LearningCode0
Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation LearningCode0
Contrastive Latent Variable Models for Neural Text GenerationCode0
Show:102550
← PrevPage 102 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