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 5701–5725 of 6661 papers

TitleStatusHype
Towards Learning (Dis)-Similarity of Source Code from Program Contrasts—0
SCaLa: Supervised Contrastive Learning for End-to-End Speech Recognition—0
Contrastive String Representation Learning using Synthetic Data—0
Phone-to-audio alignment without text: A Semi-supervised ApproachCode1
3D Infomax improves GNNs for Molecular Property PredictionCode1
Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot FillingCode1
Using Contrastive Learning and Pseudolabels to learn representations for Retail Product Image Classification—0
Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source DataCode1
MC-LCR: Multi-modal contrastive classification by locally correlated representations for effective face forgery detection—0
Cut the CARP: Fishing for zero-shot story evaluation—0
Contrastive Learning for Unsupervised Radar Place Recognition—0
The Power of Contrast for Feature Learning: A Theoretical Analysis—0
ActiveMatch: End-to-end Semi-supervised Active Representation Learning—0
KNN-BERT: Fine-Tuning Pre-Trained Models with KNN ClassifierCode1
The Information Geometry of Unsupervised Reinforcement LearningCode1
ProGCL: Rethinking Hard Negative Mining in Graph Contrastive LearningCode1
Multi-axis Attentive Prediction for Sparse EventData: An Application to Crime PredictionCode0
SeanNet: Semantic Understanding Network for Localization Under Object DynamicsCode0
Deep Fraud Detection on Non-attributed Graph—0
Using Out-of-the-Box Frameworks for Contrastive Unpaired Image Translation for Vestibular Schwannoma and Cochlea Segmentation: An approach for the crossMoDA Challenge—0
Consistent Explanations by Contrastive LearningCode1
Stochastic Contrastive Learning—0
Motion-aware Contrastive Video Representation Learning via Foreground-background MergingCode1
CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations—0
Key Point Analysis via Contrastive Learning and Extractive Argument SummarizationCode0
Show:102550
← PrevPage 229 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