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 476–500 of 6661 papers

TitleStatusHype
KDMCSE: Knowledge Distillation Multimodal Sentence Embeddings with Adaptive Angular margin Contrastive LearningCode1
HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text ClassificationCode1
Graph Augmentation for RecommendationCode1
GTC: GNN-Transformer Co-contrastive Learning for Self-supervised Heterogeneous Graph RepresentationCode1
GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity LearningCode1
Towards Principled Representation Learning from Videos for Reinforcement LearningCode1
Non-negative Contrastive LearningCode1
Do Generated Data Always Help Contrastive Learning?Code1
GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised LearningCode1
Open-World Semi-Supervised Learning for Node ClassificationCode1
Is Contrastive Learning Necessary? A Study of Data Augmentation vs Contrastive Learning in Sequential RecommendationCode1
Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling CasesCode1
EquiAV: Leveraging Equivariance for Audio-Visual Contrastive LearningCode1
Counterfactual contrastive learning: robust representations via causal image synthesisCode1
Dyadic Interaction Modeling for Social Behavior GenerationCode1
GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D UnderstandingCode1
Hyper-CL: Conditioning Sentence Representations with HypernetworksCode1
Decoupled Contrastive Learning for Long-Tailed RecognitionCode1
Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive LearningCode1
Self-Adapting Large Visual-Language Models to Edge Devices across Visual ModalitiesCode1
Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation DistillationCode1
Inference via Interpolation: Contrastive Representations Provably Enable Planning and InferenceCode1
FedHCDR: Federated Cross-Domain Recommendation with Hypergraph Signal DecouplingCode1
A Unified Framework for Microscopy Defocus Deblur with Multi-Pyramid Transformer and Contrastive LearningCode1
Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source LocalizationCode1
Show:102550
← PrevPage 20 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