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 5851–5900 of 6661 papers

TitleStatusHype
Information Theory-Guided Heuristic Progressive Multi-View Coding—0
Sensor Data Augmentation by Resampling for Contrastive Learning in Human Activity Recognition—0
The Phonexia VoxCeleb Speaker Recognition Challenge 2021 System Description—0
Semantics-Guided Contrastive Network for Zero-Shot Object detection—0
Supervised Contrastive Learning for Multimodal Unreliable News Detection in COVID-19 PandemicCode1
Hybrid Contrastive Learning of Tri-Modal Representation for Multimodal Sentiment Analysis—0
Contrastive Representation Learning for Exemplar-Guided Paraphrase GenerationCode1
Complementary Calibration: Boosting General Continual Learning with Collaborative Distillation and Self-SupervisionCode0
Revisiting 3D ResNets for Video RecognitionCode0
Self-supervised Pseudo Multi-class Pre-training for Unsupervised Anomaly Detection and Segmentation in Medical ImagesCode1
Motifs-based Recommender System via Hypergraph Convolution and Contrastive LearningCode0
Self-supervised Representation Learning for Trip Recommendation—0
Imposing Relation Structure in Language-Model Embeddings Using Contrastive LearningCode1
Memory Augmented Multi-Instance Contrastive Predictive Coding for Sequential RecommendationCode1
ReMeDi: Resources for Multi-domain, Multi-service, Medical DialoguesCode1
Multi-Sample based Contrastive Loss for Top-k RecommendationCode1
Structure-Aware Hard Negative Mining for Heterogeneous Graph Contrastive Learning—0
ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasetsCode1
Injecting Text in Self-Supervised Speech Pretraining—0
Learning Cross-modal Contrastive Features for Video Domain Adaptation—0
Enhanced Seq2Seq Autoencoder via Contrastive Learning for Abstractive Text SummarizationCode1
MCML: A Novel Memory-based Contrastive Meta-Learning Method for Few Shot Slot Tagging—0
When Do Contrastive Learning Signals Help Spatio-Temporal Graph Forecasting?Code1
Alleviating Exposure Bias via Contrastive Learning for Abstractive Text SummarizationCode1
EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning—0
ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning—0
Graph Contrastive Pre-training for Effective Theorem Reasoning—0
Contrastive Learning of User Behavior Sequence for Context-Aware Document RankingCode1
Support-Set Based Cross-Supervision for Video Grounding—0
Self-Supervised Graph Co-Training for Session-based RecommendationCode1
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment—0
Generative and Contrastive Self-Supervised Learning for Graph Anomaly DetectionCode1
Unsupervised Local Discrimination for Medical ImagesCode1
Supervised Contrastive Learning for Interpretable Long-Form Document MatchingCode0
Group-based Distinctive Image Captioning with Memory Attention—0
Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text ModelsCode1
Self-Supervised Video Representation Learning with Meta-Contrastive Network—0
Feature Stylization and Domain-aware Contrastive Learning for Domain GeneralizationCode1
ALBRT: Cellular Composition Prediction in Routine Histology ImagesCode0
Graph Contrastive Learning for Anomaly DetectionCode1
Self-Supervised Pretraining and Controlled Augmentation Improve Rare Wildlife Recognition in UAV ImagesCode0
RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object DetectionCode1
Deep Contrastive Multiview Network Embedding—0
Scene Designer: a Unified Model for Scene Search and Synthesis from SketchCode1
Unsupervised Person Re-identification with Stochastic Training StrategyCode0
Self-supervised Contrastive Learning of Multi-view Facial Expressions—0
Contrastive Self-supervised Sequential Recommendation with Robust AugmentationCode1
Unsupervised Disentanglement without Autoencoding: Pitfalls and Future DirectionsCode0
Collaborative Unsupervised Visual Representation Learning from Decentralized DataCode0
GeoCLR: Georeference Contrastive Learning for Efficient Seafloor Image Interpretation—0
Show:102550
← PrevPage 118 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