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 5951–5975 of 6661 papers

TitleStatusHype
Token-Level Supervised Contrastive Learning for Punctuation RestorationCode1
Using system context information to complement weakly labeled data—0
Compound Figure Separation of Biomedical Images with Side LossCode0
OODformer: Out-Of-Distribution Detection TransformerCode1
Lesion-based Contrastive Learning for Diabetic Retinopathy Grading from Fundus ImagesCode1
Self-supervised Representation Learning Framework for Remote Physiological Measurement Using Spatiotemporal Augmentation LossCode1
Contrastive Predictive Coding for Anomaly Detection—0
Towards an Interpretable Latent Space in Structured Models for Video Prediction—0
More Robust Dense Retrieval with Contrastive Dual LearningCode1
Multi-Level Contrastive Learning for Few-Shot Problems—0
Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based AttacksCode0
Generative Adversarial Learning via Kernel Density Discrimination—0
Anatomy-Constrained Contrastive Learning for Synthetic Segmentation without Ground-truthCode1
Contrastive Learning for Cold-Start RecommendationCode1
Segmentation of VHR EO Images using Unsupervised Learning—0
3D Neural Scene Representations for Visuomotor Control—0
Staying in Shape: Learning Invariant Shape Representations using Contrastive Learning—0
Joint Embedding of Structural and Functional Brain Networks with Graph Neural Networks for Mental Illness Diagnosis—0
HCGR: Hyperbolic Contrastive Graph Representation Learning for Session-based Recommendation—0
Improving Text-to-Image Synthesis Using Contrastive LearningCode1
A Hierarchical Dual Model of Environment- and Place-Specific Utility for Visual Place RecognitionCode1
Multi-Level Graph Contrastive Learning—0
Contrastive Multimodal Fusion with TupleInfoNCECode1
Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning—0
Continual Contrastive Learning for Image ClassificationCode0
Show:102550
← PrevPage 239 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