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 6051–6075 of 6661 papers

TitleStatusHype
Sentence Embeddings using Supervised Contrastive LearningCode0
Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive LossCode1
Contrastive Representation Learning for Hand Shape Estimation—0
Learning Markov State Abstractions for Deep Reinforcement LearningCode1
Shifting Transformation Learning for Out-of-Distribution Detection—0
Socially-Aware Self-Supervised Tri-Training for RecommendationCode2
Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast—0
Enabling On-Device Self-Supervised Contrastive Learning With Selective Data Contrast—0
Mean-Shifted Contrastive Loss for Anomaly DetectionCode1
Incremental False Negative Detection for Contrastive Learning—0
Self-Damaging Contrastive LearningCode1
Understand and Improve Contrastive Learning Methods for Visual Representation: A Review—0
MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular GraphCode1
Integrating Auxiliary Information in Self-supervised Learning—0
Category Contrast for Unsupervised Domain Adaptation in Visual TasksCode1
Conditional Contrastive Learning for Improving Fairness in Self-Supervised Learning—0
Graph Barlow Twins: A self-supervised representation learning framework for graphsCode1
Aligning Pretraining for Detection via Object-Level Contrastive LearningCode1
Bi-Granularity Contrastive Learning for Post-Training in Few-Shot Scene—0
Self-Guided Contrastive Learning for BERT Sentence RepresentationsCode1
TVDIM: Enhancing Image Self-Supervised Pretraining via Noisy Text Data—0
SimCLS: A Simple Framework for Contrastive Learning of Abstractive SummarizationCode1
Semantic-Aware Contrastive Learning for Multi-object Medical Image Segmentation—0
You Never Cluster Alone—0
Adversarial Self-Supervised Learning for Out-of-Domain DetectionCode0
Show:102550
← PrevPage 243 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