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 1251–1300 of 6661 papers

TitleStatusHype
Biomedical Entity Linking with Contrastive Context MatchingCode1
Multi-level Feature Learning for Contrastive Multi-view ClusteringCode1
Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive LearningCode1
Generative Retrieval with Semantic Tree-Structured Item Identifiers via Contrastive LearningCode1
Contrastive Learning Improves Model Robustness Under Label NoiseCode1
GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised LearningCode1
CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at ScaleCode1
Geography-Aware Self-Supervised LearningCode1
Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space ViewpointCode1
Contrastive Multiview CodingCode1
Denoising-Aware Contrastive Learning for Noisy Time SeriesCode1
GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity LearningCode1
ConDA: Contrastive Domain Adaptation for AI-generated Text DetectionCode1
Contrastive Neural Processes for Self-Supervised LearningCode1
GMSS: Graph-Based Multi-Task Self-Supervised Learning for EEG Emotion RecognitionCode1
Contrastive Learning for Cold-Start RecommendationCode1
Deep Robust Clustering by Contrastive LearningCode1
Deep Multiview Clustering by Contrasting Cluster AssignmentsCode1
Black-Box Attack against GAN-Generated Image Detector with Contrastive PerturbationCode1
Alleviating Exposure Bias via Contrastive Learning for Abstractive Text SummarizationCode1
Deep Multi-View Subspace Clustering with Anchor GraphCode1
Contrastive Learning for Cross-Domain Open World RecognitionCode1
Black Box Few-Shot Adaptation for Vision-Language modelsCode1
Graph-Aware Contrasting for Multivariate Time-Series ClassificationCode1
Graph Contrastive Learning AutomatedCode1
Graph Contrastive Learning for Skeleton-based Action RecognitionCode1
Blind Localization and Clustering of Anomalies in TexturesCode1
Graph Contrastive Learning with Adaptive AugmentationCode1
Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven OptimizationCode1
Contrastive Self-supervised Sequential Recommendation with Robust AugmentationCode1
Graph Self-supervised Learning with Accurate Discrepancy LearningCode1
GraSS: Contrastive Learning with Gradient Guided Sampling Strategy for Remote Sensing Image Semantic SegmentationCode1
Contrastive Learning for Improving ASR Robustness in Spoken Language UnderstandingCode1
Group-wise Contrastive Learning for Neural Dialogue GenerationCode1
Contrastive Positive Sample Propagation along the Audio-Visual Event LineCode1
G-SimCLR : Self-Supervised Contrastive Learning with Guided Projection via Pseudo LabellingCode1
Contrastive Learning for Knowledge TracingCode1
H2CGL: Modeling Dynamics of Citation Network for Impact PredictionCode1
Boosting Contrastive Self-Supervised Learning with False Negative CancellationCode1
Hard Negative Mixing for Contrastive LearningCode1
HC-GLAD: Dual Hyperbolic Contrastive Learning for Unsupervised Graph-Level Anomaly DetectionCode1
HCSC: Hierarchical Contrastive Selective CodingCode1
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action RecognitionCode1
HEAL: Hierarchical Embedding Alignment Loss for Improved Retrieval and Representation LearningCode1
Automated Essay Scoring via Pairwise Contrastive RegressionCode1
Contrastive Learning for Many-to-many Multilingual Neural Machine TranslationCode1
Contrastive Learning for Sequential RecommendationCode1
Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Adaptively Weighted Negative SamplesCode1
Contrastive Learning for Neural Topic ModelCode1
ConCL: Concept Contrastive Learning for Dense Prediction Pre-training in Pathology ImagesCode1
Show:102550
← PrevPage 26 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