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 1601–1650 of 6661 papers

TitleStatusHype
Change-Aware Sampling and Contrastive Learning for Satellite ImagesCode1
Bridging Spectral-wise and Multi-spectral Depth Estimation via Geometry-guided Contrastive LearningCode1
Transferring Unconditional to Conditional GANs with Hyper-ModulationCode1
Hierarchical Self-Supervised Adversarial Training for Robust Vision Models in HistopathologyCode1
Hierarchical Skeleton Meta-Prototype Contrastive Learning with Hard Skeleton Mining for Unsupervised Person Re-IdentificationCode1
Hierarchical Time-Aware Mixture of Experts for Multi-Modal Sequential RecommendationCode1
Learning to Retrieve Passages without SupervisionCode1
Cross-modal Causal Relation Alignment for Video Question GroundingCode1
Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation OverlapCode1
HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text ClassificationCode1
Cross-modal Contrastive Learning for Multimodal Fake News DetectionCode1
A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-IdentificationCode1
HMIL: Hierarchical Multi-Instance Learning for Fine-Grained Whole Slide Image ClassificationCode1
Cross-modal Contrastive Learning for Speech TranslationCode1
Cross-Modal Contrastive Learning for Text-to-Image GenerationCode1
Cross-Modal Contrastive Learning of Representations for Navigation using Lightweight, Low-Cost Millimeter Wave Radar for Adverse Environmental ConditionsCode1
ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense RetrievalCode1
Cross-Modal Information-Guided Network using Contrastive Learning for Point Cloud RegistrationCode1
Learning to Revise References for Faithful SummarizationCode1
Cross-Modal Retrieval with Partially Mismatched PairsCode1
PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive LearningCode1
Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton SequencesCode1
Hybrid Contrastive Quantization for Efficient Cross-View Video RetrievalCode1
Cross-Patch Dense Contrastive Learning for Semi-Supervised Segmentation of Cellular Nuclei in Histopathologic ImagesCode1
DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time SeriesCode1
Hybrid Generative-Contrastive Representation LearningCode1
D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance AnnotationCode1
Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled DataCode1
CUTS: A Deep Learning and Topological Framework for Multigranular Unsupervised Medical Image SegmentationCode1
Hyperbolic Contrastive Learning for Visual Representations beyond ObjectsCode1
Hypergraph Contrastive Learning for Drug Trafficking Community DetectionCode1
Hypergraph Contrastive Collaborative FilteringCode1
Hyperspherical Consistency RegularizationCode1
Cross-View Geolocalization and Disaster Mapping with Street-View and VHR Satellite Imagery: A Case Study of Hurricane IANCode1
Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural NetworksCode1
Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-trainingCode1
Callee: Recovering Call Graphs for Binaries with Transfer and Contrastive LearningCode1
ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identificationCode1
Identifiability Results for Multimodal Contrastive LearningCode1
Deep Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional NetworksCode1
Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from PixelsCode1
Self-supervised Graph Neural Networks without explicit negative samplingCode1
A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence EmbeddingsCode1
CSGCL: Community-Strength-Enhanced Graph Contrastive LearningCode1
Image Quality Assessment using Contrastive LearningCode1
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted InstancesCode1
CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal ConversionCode1
IMF: Interactive Multimodal Fusion Model for Link PredictionCode1
i-Mix: A Domain-Agnostic Strategy for Contrastive Representation LearningCode1
Learning to Embed Time Series Patches IndependentlyCode1
Show:102550
← PrevPage 33 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