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

Showing 12011225 of 6661 papers

TitleStatusHype
Cross-Domain Sentiment Classification with In-Domain Contrastive LearningCode1
Cross-Modal Contrastive Learning for Text-to-Image GenerationCode1
Contrastive Embeddings for Neural ArchitecturesCode1
Beyond Co-occurrence: Multi-modal Session-based RecommendationCode1
Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive AlignmentCode1
Improving Music Performance Assessment with Contrastive LearningCode1
Conditional Contrastive Learning with KernelCode1
Cross-level Contrastive Learning and Consistency Constraint for Semi-supervised Medical Image SegmentationCode1
Adaptive Supervised PatchNCE Loss for Learning H&E-to-IHC Stain Translation with Inconsistent Groundtruth Image PairsCode1
Contrastive Fine-grained Class Clustering via Generative Adversarial NetworksCode1
Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure LearningCode1
Cross-modal Causal Relation Alignment for Video Question GroundingCode1
Cross-modal Contrastive Learning for Multimodal Fake News DetectionCode1
Improving Word Translation via Two-Stage Contrastive LearningCode1
Cross-Modal Information-Guided Network using Contrastive Learning for Point Cloud RegistrationCode1
Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-trainingCode1
CURL: Contrastive Unsupervised Representation Learning for Reinforcement LearningCode1
Cross-Modal Retrieval with Partially Mismatched PairsCode1
Automated Spatio-Temporal Graph Contrastive LearningCode1
Cross-Patch Dense Contrastive Learning for Semi-Supervised Segmentation of Cellular Nuclei in Histopathologic ImagesCode1
Graph Contrastive Invariant Learning from the Causal PerspectiveCode1
Cross-Silo Prototypical Calibration for Federated Learning with Non-IID DataCode1
Contrastive Grouping with Transformer for Referring Image SegmentationCode1
AD-CLIP: Adapting Domains in Prompt Space Using CLIPCode1
Graph Contrastive Learning Meets Graph Meta Learning: A Unified Method for Few-shot Node TasksCode1
Show:102550
← PrevPage 49 of 267Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6Unverified
2ResNet50ImageNet Top-1 Accuracy73Unverified
3ResNet50ImageNet Top-1 Accuracy71.1Unverified
4ResNet50ImageNet Top-1 Accuracy69.3Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8Unverified
7ResNet50ImageNet Top-1 Accuracy63.6Unverified
8ResNet50ImageNet Top-1 Accuracy61.5Unverified
9ResNet50ImageNet Top-1 Accuracy61.5Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55Unverified