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 6401–6450 of 6661 papers

TitleStatusHype
CoMatch: Semi-supervised Learning with Contrastive Graph RegularizationCode1
Exploring Contrastive Learning in Human Activity Recognition for HealthcareCode1
Hierarchically Decoupled Spatial-Temporal Contrast for Self-supervised Video Representation Learning—0
Run Away From your Teacher: Understanding BYOL by a Novel Self-Supervised Approach—0
Geography-Aware Self-Supervised LearningCode1
Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation LearningCode1
Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations—0
Dense Contrastive Learning for Self-Supervised Visual Pre-TrainingCode1
Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive LearningCode1
Contrastive Registration for Unsupervised Medical Image SegmentationCode1
Self-supervised Document Clustering Based on BERT with Data Augment—0
Can Semantic Labels Assist Self-Supervised Visual Representation Learning?—0
AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative AdversariesCode1
Combating the Instability of Mutual Information-based Losses via RegularizationCode0
On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?—0
Unsupervised Contrastive Learning of Sound Event RepresentationsCode1
Bi-tuning of Pre-trained Representations—0
Unsupervised Video Representation Learning by Bidirectional Feature Prediction—0
Unsupervised Learning of Dense Visual Representations—0
Towards Domain-Agnostic Contrastive Learning—0
Self-Supervised Learning from Contrastive Mixtures for Personalized Speech EnhancementCode0
Intriguing Properties of Contrastive LossesCode2
Center-wise Local Image Mixture For Contrastive Representation Learning—0
CODER: Knowledge infused cross-lingual medical term embedding for term normalizationCode1
Learning and Evaluating Representations for Deep One-class ClassificationCode1
Supervised Contrastive Learning for Pre-trained Language Model Fine-tuningCode1
Semi-supervised Facial Action Unit Intensity Estimation with Contrastive Learning—0
Learning to Contrast the Counterfactual Samples for Robust Visual Question AnsweringCode1
Distilling Structured Knowledge for Text-Based Relational Reasoning—0
A Survey on Contrastive Self-supervised Learning—0
Self-supervised Representation Learning for Evolutionary Neural Architecture SearchCode0
Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information MaximizationCode1
When Contrastive Learning Meets Active Learning: A Novel Graph Active Learning Paradigm with Self-Supervision—0
Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video Representation LeaningCode1
Cycle-Contrast for Self-Supervised Video Representation Learning—0
Graph Contrastive Learning with Adaptive AugmentationCode1
Contrastive Learning for Sequential RecommendationCode1
Robust Pre-Training by Adversarial Contrastive LearningCode1
Contrastive Unsupervised Learning for Audio Fingerprinting—0
CLRGaze: Contrastive Learning of Representations for Eye Movement SignalsCode0
Iterative Graph Self-Distillation—0
CLOUD: Contrastive Learning of Unsupervised Dynamics—0
Multilingual BERT Post-Pretraining Alignment—0
Momentum Contrast Speaker Representation Learning—0
Graph Contrastive Learning with AugmentationsCode1
Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction PredictionCode1
Contrastive Learning with Adversarial Examples—0
A Framework for Generative and Contrastive Learning of Audio Representations—0
Neural Audio Fingerprint for High-specific Audio Retrieval based on Contrastive LearningCode1
Contrastive Self-Supervised Learning for Wireless Power ControlCode0
Show:102550
← PrevPage 129 of 134Next →
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