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 5901–5950 of 6661 papers

TitleStatusHype
Pcc-tuning: Breaking the Contrastive Learning Ceiling in Semantic Textual SimilarityCode0
PCLMix: Weakly Supervised Medical Image Segmentation via Pixel-Level Contrastive Learning and Dynamic Mix AugmentationCode0
What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood ContextCode0
Into the Unknown: Applying Inductive Spatial-Semantic Location Embeddings for Predicting Individuals' Mobility Beyond Visited PlacesCode0
Interventional Video Grounding with Dual Contrastive LearningCode0
CoRTEx: Contrastive Learning for Representing Terms via Explanations with Applications on Constructing Biomedical Knowledge GraphsCode0
Smoothed Graph Contrastive Learning via Seamless Proximity IntegrationCode0
Adversarial Momentum-Contrastive Pre-TrainingCode0
PECon: Contrastive Pretraining to Enhance Feature Alignment between CT and EHR Data for Improved Pulmonary Embolism DiagnosisCode0
Words Matter: Leveraging Individual Text Embeddings for Code Generation in CLIP Test-Time AdaptationCode0
Correlation between Alignment-Uniformity and Performance of Dense Contrastive RepresentationsCode0
COROLLA: An Efficient Multi-Modality Fusion Framework with Supervised Contrastive Learning for Glaucoma GradingCode0
PE-GAN: Prior Embedding GAN for PXD images at Belle IICode0
Coreference Graph Guidance for Mind-Map GenerationCode0
Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene SegmentationCode0
PepHarmony: A Multi-View Contrastive Learning Framework for Integrated Sequence and Structure-Based Peptide EncodingCode0
COOKIE: Contrastive Cross-Modal Knowledge Sharing Pre-Training for Vision-Language RepresentationCode0
Contrastive Learning Augmented Social RecommendationsCode0
Perfect Alignment May be Poisonous to Graph Contrastive LearningCode0
Intermediate Domain-guided Adaptation for Unsupervised Chorioallantoic Membrane Vessel SegmentationCode0
Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic DataCode0
Controlled Text Generation with Hidden Representation TransformationsCode0
Towards Robust Multimodal Representation: A Unified Approach with Adaptive Experts and AlignmentCode0
Personalized LLM for Generating Customized Responses to the Same Query from Different UsersCode0
SoftMCL: Soft Momentum Contrastive Learning for Fine-grained Sentiment-aware Pre-trainingCode0
Adversarial Modality Alignment Network for Cross-Modal Molecule RetrievalCode0
Interactive Dimensionality Reduction for Comparative AnalysisCode0
Contrastive Visual-Linguistic PretrainingCode0
Unsupervised Graph Clustering with Deep Structural EntropyCode0
Intensity-Spatial Dual Masked Autoencoder for Multi-Scale Feature Learning in Chest CT SegmentationCode0
Contrastive Variational Autoencoder Enhances Salient FeaturesCode0
CLHA: A Simple yet Effective Contrastive Learning Framework for Human AlignmentCode0
PFML: Self-Supervised Learning of Time-Series Data Without Representation CollapseCode0
Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person SearchCode0
CLDR: Contrastive Learning Drug Response Models from Natural Language SupervisionCode0
A Contrastive Learning Scheme with Transformer Innate PatchesCode0
Integrating Deep Metric Learning with Coreset for Active Learning in 3D SegmentationCode0
Sounding Video Generator: A Unified Framework for Text-guided Sounding Video GenerationCode0
Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from ImagesCode0
Phrase Retrieval for Open-Domain Conversational Question Answering with Conversational Dependency Modeling via Contrastive LearningCode0
Instance Smoothed Contrastive Learning for Unsupervised Sentence EmbeddingCode0
PICL: Physics Informed Contrastive Learning for Partial Differential EquationsCode0
In-sample Contrastive Learning and Consistent Attention for Weakly Supervised Object LocalizationCode0
Sound Localization by Self-Supervised Time Delay EstimationCode0
Contrastive Training of Complex-Valued Autoencoders for Object DiscoveryCode0
Noise-robust Graph Learning by Estimating and Leveraging Pairwise InteractionsCode0
PiPViT: Patch-based Visual Interpretable Prototypes for Retinal Image AnalysisCode0
Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for HistologyCode0
Contrastive Self-Supervised Learning for Wireless Power ControlCode0
Contrastive Self-Supervised Learning Based Approach for Patient Similarity: A Case Study on Atrial Fibrillation Detection from PPG SignalCode0
Show:102550
← PrevPage 119 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