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 451–500 of 6661 papers

TitleStatusHype
Cross-Modal Information-Guided Network using Contrastive Learning for Point Cloud RegistrationCode1
Cross-Modal Retrieval with Partially Mismatched PairsCode1
Contrastive Code Representation LearningCode1
Self-Supervised Time Series Representation Learning via Cross Reconstruction TransformerCode1
CSGCL: Community-Strength-Enhanced Graph Contrastive LearningCode1
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted InstancesCode1
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual RepresentationsCode1
Towards Cross-Table Masked Pretraining for Web Data MiningCode1
CUTS: A Deep Learning and Topological Framework for Multigranular Unsupervised Medical Image SegmentationCode1
CycleGuardian: A Framework for Automatic RespiratorySound classification Based on Improved Deep clustering and Contrastive LearningCode1
DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time SeriesCode1
Data Augmentation-free Unsupervised Learning for 3D Point Cloud UnderstandingCode1
Anomaly Detection on Attributed Networks via Contrastive Self-Supervised LearningCode1
Data Poisoning based Backdoor Attacks to Contrastive LearningCode1
AIRCHITECT v2: Learning the Hardware Accelerator Design Space through Unified RepresentationsCode1
Contrastive Collaborative Filtering for Cold-Start Item RecommendationCode1
Anomaly Detection in IR Images of PV Modules using Supervised Contrastive LearningCode1
Debiased Contrastive LearningCode1
Behavior Contrastive Learning for Unsupervised Skill DiscoveryCode1
Debiased Contrastive Learning of Unsupervised Sentence RepresentationsCode1
Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation DistillationCode1
Contrastive Denoising Score for Text-guided Latent Diffusion Image EditingCode1
A Language Model based Framework for New Concept Placement in OntologiesCode1
Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial RobustnessCode1
A latent space for unsupervised MR image quality control via artifact assessmentCode1
Biomedical Entity Linking with Contrastive Context MatchingCode1
Actionness Inconsistency-guided Contrastive Learning for Weakly-supervised Temporal Action LocalizationCode1
Contrastive Learning for Compact Single Image DehazingCode1
A class-weighted supervised contrastive learning long-tailed bearing fault diagnosis approach using quadratic neural networkCode1
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional UnderstandingCode1
BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and MappingCode1
Deep Graph Contrastive Representation LearningCode1
Deep Robust Clustering by Contrastive LearningCode1
Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven OptimizationCode1
CONTRASTE: Supervised Contrastive Pre-training With Aspect-based Prompts For Aspect Sentiment Triplet ExtractionCode1
Audio Retrieval with WavText5K and CLAP TrainingCode1
AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive LearningCode1
Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-SeriesCode1
Audio-Visual Instance Discrimination with Cross-Modal AgreementCode1
Audio-Visual Person-of-Interest DeepFake DetectionCode1
Density-invariant Features for Distant Point Cloud RegistrationCode1
Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic SegmentationCode1
Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited ModalitiesCode1
Contrast and Classify: Training Robust VQA ModelsCode1
ContraNovo: A Contrastive Learning Approach to Enhance De Novo Peptide SequencingCode1
Augmentations in Hypergraph Contrastive Learning: Fabricated and GenerativeCode1
Contrast and Generation Make BART a Good Dialogue Emotion RecognizerCode1
Augmented Dual-Contrastive Aggregation Learning for Unsupervised Visible-Infrared Person Re-IdentificationCode1
Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action RecognitionCode1
ContraCLM: Contrastive Learning For Causal Language ModelCode1
Show:102550
← PrevPage 10 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