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 401–450 of 6661 papers

TitleStatusHype
ContraNorm: A Contrastive Learning Perspective on Oversmoothing and BeyondCode1
A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-IdentificationCode1
A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment AnalysisCode1
A Self-supervised Method for Entity AlignmentCode1
Contrastive Learning Reduces Hallucination in ConversationsCode1
Anomaly Detection in IR Images of PV Modules using Supervised Contrastive LearningCode1
Contrastive Learning with Boosted MemorizationCode1
Contrastive Learning with Continuous Proxy Meta-Data for 3D MRI ClassificationCode1
Contrastive Learning with Hard Negative Entities for Entity Set ExpansionCode1
A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence EmbeddingsCode1
Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical ReasoningCode1
Contrastive Learning with Stronger AugmentationsCode1
A Simple and Effective Self-Supervised Contrastive Learning Framework for Aspect DetectionCode1
Contrastive Masked Autoencoders are Stronger Vision LearnersCode1
Continuous Learning for Android Malware DetectionCode1
A Simple Contrastive Learning Objective for Alleviating Neural Text DegenerationCode1
A simple, efficient and scalable contrastive masked autoencoder for learning visual representationsCode1
ContraBAR: Contrastive Bayes-Adaptive Deep RLCode1
Contrastive Out-of-Distribution Detection for Pretrained TransformersCode1
Contrastive Positive Sample Propagation along the Audio-Visual Event LineCode1
A Simple Graph Contrastive Learning Framework for Short Text ClassificationCode1
A Simple Long-Tailed Recognition Baseline via Vision-Language ModelCode1
ContraNovo: A Contrastive Learning Approach to Enhance De Novo Peptide SequencingCode1
A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation ExtractionCode1
Contrastive Representation Learning for Dynamic Link Prediction in Temporal NetworksCode1
Contrastive Representation Learning for Gaze EstimationCode1
Contrastive Self-supervised Sequential Recommendation with Robust AugmentationCode1
Contrastive Semi-supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical StructuresCode1
Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video RepresentationCode1
Contrastive Test-Time AdaptationCode1
Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-SeriesCode1
Contrastive Video Question Answering via Video Graph TransformerCode1
Assisting Mathematical Formalization with A Learning-based Premise RetrieverCode1
Contrastive Vision-Language Alignment Makes Efficient Instruction LearnerCode1
Learning the Unlearned: Mitigating Feature Suppression in Contrastive LearningCode1
AstroCLIP: A Cross-Modal Foundation Model for GalaxiesCode1
Contrast then Memorize: Semantic Neighbor Retrieval-Enhanced Inductive Multimodal Knowledge Graph CompletionCode1
ContrastVAE: Contrastive Variational AutoEncoder for Sequential RecommendationCode1
A Supervised Information Enhanced Multi-Granularity Contrastive Learning Framework for EEG Based Emotion RecognitionCode1
Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious CorrelationsCode1
A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural NetworksCode1
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive LearningCode1
Contrastive Deep SupervisionCode1
COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive LearningCode1
CoT-BERT: Enhancing Unsupervised Sentence Representation through Chain-of-ThoughtCode1
Contrastive Domain Adaptation for Time-Series via Temporal MixupCode1
A Hierarchical Dual Model of Environment- and Place-Specific Utility for Visual Place RecognitionCode1
Contrastive learning for regression in multi-site brain age predictionCode1
Balanced Contrastive Learning for Long-Tailed Visual RecognitionCode1
A class-weighted supervised contrastive learning long-tailed bearing fault diagnosis approach using quadratic neural networkCode1
Show:102550
← PrevPage 9 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