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 501–550 of 6661 papers

TitleStatusHype
Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot LearningCode1
Efficient Action Counting with Dynamic QueriesCode1
Applying Self-supervised Learning to Network Intrusion Detection for Network Flows with Graph Neural NetworkCode1
MMSR: Symbolic Regression is a Multi-Modal Information Fusion TaskCode1
Polos: Multimodal Metric Learning from Human Feedback for Image CaptioningCode1
A Language Model based Framework for New Concept Placement in OntologiesCode1
Label Informed Contrastive Pretraining for Node Importance Estimation on Knowledge GraphsCode1
E2USD: Efficient-yet-effective Unsupervised State Detection for Multivariate Time SeriesCode1
Triple-Encoders: Representations That Fire Together, Wire TogetherCode1
Learning the Unlearned: Mitigating Feature Suppression in Contrastive LearningCode1
Continuous Multi-Task Pre-training for Malicious URL Detection and Webpage ClassificationCode1
Parametric Augmentation for Time Series Contrastive LearningCode1
MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained RepresentationsCode1
MM-Point: Multi-View Information-Enhanced Multi-Modal Self-Supervised 3D Point Cloud UnderstandingCode1
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive LossCode1
Boundary-aware Contrastive Learning for Semi-supervised Nuclei Instance SegmentationCode1
TimeSiam: A Pre-Training Framework for Siamese Time-Series ModelingCode1
BECLR: Batch Enhanced Contrastive Few-Shot LearningCode1
Prototypical Contrastive Learning through Alignment and Uniformity for RecommendationCode1
Variance Alignment Score: A Simple But Tough-to-Beat Data Selection Method for Multimodal Contrastive LearningCode1
Root Cause Analysis In Microservice Using Neural Granger Causal DiscoveryCode1
Graph Contrastive Learning with Cohesive Subgraph AwarenessCode1
Supervised Contrastive Learning based Dual-Mixer Model for Remaining Useful Life PredictionCode1
Contrastive Learning and Mixture of Experts Enables Precise Vector EmbeddingsCode1
RecDCL: Dual Contrastive Learning for RecommendationCode1
LegalDuet: Learning Fine-grained Representations for Legal Judgment Prediction via a Dual-View Contrastive LearningCode1
Improving Antibody Humanness Prediction using Patent DataCode1
DenoSent: A Denoising Objective for Self-Supervised Sentence Representation LearningCode1
Graph Contrastive Invariant Learning from the Causal PerspectiveCode1
Multimodal Visual-Tactile Representation Learning through Self-Supervised Contrastive Pre-TrainingCode1
Unifying Visual and Vision-Language Tracking via Contrastive LearningCode1
Spatial-temporal Forecasting for Regions without ObservationsCode1
Learning High-Quality and General-Purpose Phrase RepresentationsCode1
PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly DetectionCode1
Question-Answer Cross Language Image Matching for Weakly Supervised Semantic SegmentationCode1
Explaining Time Series via Contrastive and Locally Sparse PerturbationsCode1
HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image RetrievalCode1
Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI FeedbackCode1
Relaxed Contrastive Learning for Federated LearningCode1
Self-supervised speech representation and contextual text embedding for match-mismatch classification with EEG recordingCode1
Contrastive Viewpoint-aware Shape Learning for Long-term Person Re-IdentificationCode1
Multi-modal vision-language model for generalizable annotation-free pathology localization and clinical diagnosisCode1
Motif-aware Riemannian Graph Neural Network with Generative-Contrastive LearningCode1
Positive-Unlabeled Learning by Latent Group-Aware Meta DisambiguationCode1
Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-IdentificationCode1
Data Poisoning based Backdoor Attacks to Contrastive LearningCode1
PH-Net: Semi-Supervised Breast Lesion Segmentation via Patch-wise HardnessCode1
Weakly Supervised Video Individual CountingCode1
Instance-aware Contrastive Learning for Occluded Human Mesh ReconstructionCode1
Mitigating the Impact of False Negatives in Dense Retrieval with Contrastive Confidence RegularizationCode1
Show:102550
← PrevPage 11 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