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 551–575 of 6661 papers

TitleStatusHype
Anatomy-Constrained Contrastive Learning for Synthetic Segmentation without Ground-truthCode1
Contrastive Learning and Mixture of Experts Enables Precise Vector EmbeddingsCode1
Contrastive Learning for Compact Single Image DehazingCode1
Contrastive Learning for Many-to-many Multilingual Neural Machine TranslationCode1
Contrastive Learning Is Spectral Clustering On Similarity GraphCode1
Contrastive Mean Teacher for Domain Adaptive Object DetectorsCode1
COPNER: Contrastive Learning with Prompt Guiding for Few-shot Named Entity RecognitionCode1
Contrastive Embeddings for Neural ArchitecturesCode1
Contrastive Fine-grained Class Clustering via Generative Adversarial NetworksCode1
Black-Box Attack against GAN-Generated Image Detector with Contrastive PerturbationCode1
Anatomical Invariance Modeling and Semantic Alignment for Self-supervised Learning in 3D Medical Image AnalysisCode1
Contrastive Denoising Score for Text-guided Latent Diffusion Image EditingCode1
Contrastive Grouping with Transformer for Referring Image SegmentationCode1
Anatomical Foundation Models for Brain MRIsCode1
Contrastive Cross-domain Recommendation in MatchingCode1
Contrastive Deep Nonnegative Matrix Factorization for Community DetectionCode1
Contrastive Collaborative Filtering for Cold-Start Item RecommendationCode1
Black Box Few-Shot Adaptation for Vision-Language modelsCode1
Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation DistillationCode1
Contrastive Deep SupervisionCode1
Contrastive Identity-Aware Learning for Multi-Agent Value DecompositionCode1
Contrastive Bayesian Analysis for Deep Metric LearningCode1
CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at ScaleCode1
AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative AdversariesCode1
Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited ModalitiesCode1
Show:102550
← PrevPage 23 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