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 3251–3275 of 6661 papers

TitleStatusHype
Discrete Contrastive Learning for Diffusion Policies in Autonomous Driving—0
Cluster Specific Representation Learning—0
Attention Weighted Mixture of Experts with Contrastive Learning for Personalized Ranking in E-commerce—0
Attention versus Contrastive Learning of Tabular Data -- A Data-centric Benchmarking—0
Discrepant and Multi-Instance Proxies for Unsupervised Person Re-Identification—0
Clustering-friendly Representation Learning for Enhancing Salient Features—0
Discovering COVID-19 Coughing and Breathing Patterns from Unlabeled Data Using Contrastive Learning with Varying Pre-Training Domains—0
Clustering disease trajectories in contrastive feature space for biomarker discovery in age-related macular degeneration—0
Attention Mechanism for Contrastive Learning in GAN-based Image-to-Image Translation—0
Enforcing View-Consistency in Class-Agnostic 3D Segmentation Fields—0
Clustering based Contrastive Learning for Improving Face Representations—0
Semantic-Aware Contrastive Learning for Multi-object Medical Image Segmentation—0
DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendation—0
Cluster-guided Contrastive Class-imbalanced Graph Classification—0
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences—0
Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimation—0
Cluster-based Contrastive Disentangling for Generalized Zero-Shot Learning—0
Attention-guided Multi-step Fusion: A Hierarchical Fusion Network for Multimodal Recommendation—0
Attention-based Interactive Disentangling Network for Instance-level Emotional Voice Conversion—0
Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition—0
Directed Link Prediction using GNN with Local and Global Feature Fusion—0
Cluster-aware Contrastive Learning for Unsupervised Out-of-distribution Detection—0
DINeMo: Learning Neural Mesh Models with no 3D Annotations—0
Cluster Analysis with Deep Embeddings and Contrastive Learning—0
DiMPLe -- Disentangled Multi-Modal Prompt Learning: Enhancing Out-Of-Distribution Alignment with Invariant and Spurious Feature Separation—0
Show:102550
← PrevPage 131 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