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 1501–1550 of 6661 papers

TitleStatusHype
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image EncodersCode1
Contrastive Viewpoint-aware Shape Learning for Long-term Person Re-IdentificationCode1
Dual Contrastive Learning: Text Classification via Label-Aware Data AugmentationCode1
3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised LearningCode1
Multimodal Clustering Networks for Self-supervised Learning from Unlabeled VideosCode1
Multimodal contrastive learning for spatial gene expression prediction using histology imagesCode1
Multimodal Contrastive Representation Learning in Augmented Biomedical Knowledge GraphsCode1
ContrastNet: A Contrastive Learning Framework for Few-Shot Text ClassificationCode1
Counterfactual contrastive learning: robust representations via causal image synthesisCode1
Capsule Network based Contrastive Learning of Unsupervised Visual RepresentationsCode1
Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic SegmentationCode1
Contrast then Memorize: Semantic Neighbor Retrieval-Enhanced Inductive Multimodal Knowledge Graph CompletionCode1
Compositional Exemplars for In-context LearningCode1
DTCLMapper: Dual Temporal Consistent Learning for Vectorized HD Map ConstructionCode1
CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly DetectionCode1
Multi-modal Siamese Network for Entity AlignmentCode1
Dual Contrastive Prediction for Incomplete Multi-view Representation LearningCode1
Multi-Objective Interpolation Training for Robustness to Label NoiseCode1
Composite Sketch+Text Queries for Retrieving Objects with Elusive Names and Complex InteractionsCode1
Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space ViewpointCode1
Multi-scale and Cross-scale Contrastive Learning for Semantic SegmentationCode1
Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation LearningCode1
CaseGNN++: Graph Contrastive Learning for Legal Case Retrieval with Graph AugmentationCode1
Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven OptimizationCode1
Multi-view Contrastive Graph ClusteringCode1
Multi-view Contrastive Learning for Online Knowledge DistillationCode1
DRIM: Learning Disentangled Representations from Incomplete Multimodal Healthcare DataCode1
Driver Anomaly Detection: A Dataset and Contrastive Learning ApproachCode1
Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based FeaturesCode1
Convolutional Cross-View Pose EstimationCode1
Category Contrast for Unsupervised Domain Adaptation in Visual TasksCode1
COPNER: Contrastive Learning with Prompt Guiding for Few-shot Named Entity RecognitionCode1
MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph DataCode1
Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio EffectsCode1
CPLIP: Zero-Shot Learning for Histopathology with Comprehensive Vision-Language AlignmentCode1
DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual ScreeningCode1
Neighborhood Contrastive Learning Applied to Online Patient MonitoringCode1
Neighborhood Contrastive Learning for Scientific Document Representations with Citation EmbeddingsCode1
A Reference-less Quality Metric for Automatic Speech Recognition via Contrastive-Learning of a Multi-Language Model with Self-SupervisionCode1
Denoising Diffusion Autoencoders are Unified Self-supervised LearnersCode1
Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious CorrelationsCode1
NeRF-Art: Text-Driven Neural Radiance Fields StylizationCode1
Dual-level Adaptive Incongruity-enhanced Model for Multimodal Sarcasm DetectionCode1
Correspondence Matters for Video Referring Expression ComprehensionCode1
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive LearningCode1
Normality Learning-based Graph Anomaly Detection via Multi-Scale Contrastive LearningCode1
Dyadic Interaction Modeling for Social Behavior GenerationCode1
A Review-aware Graph Contrastive Learning Framework for RecommendationCode1
Neural Eigenfunctions Are Structured Representation LearnersCode1
COMPLETER: Incomplete Multi-view Clustering via Contrastive PredictionCode1
Show:102550
← PrevPage 31 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