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 1751–1800 of 6661 papers

TitleStatusHype
Dense Contrastive Learning for Self-Supervised Visual Pre-TrainingCode1
Translating Electrocardiograms to Cardiac Magnetic Resonance Imaging Useful for Cardiac Assessment and Disease Screening: A Multi-Center Study AI for ECG to CMR Translation StudyCode1
miCSE: Mutual Information Contrastive Learning for Low-shot Sentence EmbeddingsCode1
Deep Boosting Learning: A Brand-new Cooperative Approach for Image-Text MatchingCode1
Large Wireless Localization Model (LWLM): A Foundation Model for Positioning in 6G NetworksCode1
Mind's Eye: Image Recognition by EEG via Multimodal Similarity-Keeping Contrastive LearningCode1
CLEVE: Contrastive Pre-training for Event ExtractionCode1
Wiener Graph Deconvolutional Network Improves Graph Self-Supervised LearningCode1
MGPATH: Vision-Language Model with Multi-Granular Prompt Learning for Few-Shot WSI ClassificationCode1
LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight DetectionCode1
LDMol: Text-to-Molecule Diffusion Model with Structurally Informative Latent SpaceCode1
Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based LearningCode1
Learning 3D Representations of Molecular Chirality with Invariance to Bond RotationsCode1
Learning and Evaluating Representations for Deep One-class ClassificationCode1
Learning Audio-Visual Source Localization via False Negative Aware Contrastive LearningCode1
Active Contrastive Learning of Audio-Visual Video RepresentationsCode1
A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural NetworksCode1
Learning Clustering-based Prototypes for Compositional Zero-shot LearningCode1
Deep Contrastive One-Class Time Series Anomaly DetectionCode1
DeepCRF: Deep Learning-Enhanced CSI-Based RF Fingerprinting for Channel-Resilient WiFi Device IdentificationCode1
Learning Efficient Coding of Natural Images with Maximum Manifold Capacity RepresentationsCode1
Learning Customized Visual Models with Retrieval-Augmented KnowledgeCode1
Learning Dialogue Representations from Consecutive UtterancesCode1
Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate ReductionCode1
A graph-transformer for whole slide image classificationCode1
Deep Graph Contrastive Representation LearningCode1
Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense InferenceCode1
Learning From Noisy Data With Robust Representation LearningCode1
CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language UnderstandingCode1
Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell CheckingCode1
Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space ViewpointCode1
MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time SeriesCode1
Learning Multi-modal Representations by Watching Hundreds of Surgical Video LecturesCode1
TimeSiam: A Pre-Training Framework for Siamese Time-Series ModelingCode1
Learning Markov State Abstractions for Deep Reinforcement LearningCode1
Democracy Does Matter: Comprehensive Feature Mining for Co-Salient Object DetectionCode1
Deep Multiview Clustering by Contrasting Cluster AssignmentsCode1
Deep Multi-View Subspace Clustering with Anchor GraphCode1
CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPCode1
Learning Non-target Knowledge for Few-shot Semantic SegmentationCode1
Reinforcement Learning Friendly Vision-Language Model for MinecraftCode1
Learning Semi-supervised Gaussian Mixture Models for Generalized Category DiscoveryCode1
A Hierarchical Dual Model of Environment- and Place-Specific Utility for Visual Place RecognitionCode1
Deep Robust Clustering by Contrastive LearningCode1
Hierarchical Time-Aware Mixture of Experts for Multi-Modal Sequential RecommendationCode1
Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-MakingCode1
MiCE: Mixture of Contrastive Experts for Unsupervised Image ClusteringCode1
Degradation-Aware Self-Attention Based Transformer for Blind Image Super-ResolutionCode1
TS2Vec: Towards Universal Representation of Time SeriesCode1
Disentangled Causal Embedding With Contrastive Learning For Recommender SystemCode1
Show:102550
← PrevPage 36 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