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 10511075 of 6661 papers

TitleStatusHype
CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked AutoencodersCode1
Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive AlignmentCode1
Cross-View Geolocalization and Disaster Mapping with Street-View and VHR Satellite Imagery: A Case Study of Hurricane IANCode1
Debiased Contrastive Learning for Sequential RecommendationCode1
CP2: Copy-Paste Contrastive Pretraining for Semantic SegmentationCode1
Counterfactual contrastive learning: robust representations via causal image synthesisCode1
Enhancing Text-based Knowledge Graph Completion with Zero-Shot Large Language Models: A Focus on Semantic EnhancementCode1
CoT-BERT: Enhancing Unsupervised Sentence Representation through Chain-of-ThoughtCode1
Temporal Context Aggregation for Video Retrieval with Contrastive LearningCode1
Contrastive Domain Adaptation for Time-Series via Temporal MixupCode1
CPLIP: Zero-Shot Learning for Histopathology with Comprehensive Vision-Language AlignmentCode1
CoSQA: 20,000+ Web Queries for Code Search and Question AnsweringCode1
CoRTX: Contrastive Framework for Real-time ExplanationCode1
COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive LearningCode1
Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious CorrelationsCode1
Correspondence Matters for Video Referring Expression ComprehensionCode1
Convolutional Cross-View Pose EstimationCode1
CONVERT:Contrastive Graph Clustering with Reliable AugmentationCode1
COPNER: Contrastive Learning with Prompt Guiding for Few-shot Named Entity RecognitionCode1
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive LearningCode1
ContrastNet: A Contrastive Learning Framework for Few-Shot Text ClassificationCode1
Automatic Biomedical Term Clustering by Learning Fine-grained Term RepresentationsCode1
Contrast-Phys+: Unsupervised and Weakly-supervised Video-based Remote Physiological Measurement via Spatiotemporal ContrastCode1
ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text EmbeddingsCode1
CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal GroundingCode1
Show:102550
← PrevPage 43 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