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 1451–1500 of 6661 papers

TitleStatusHype
Contrastive Cross-domain Recommendation in MatchingCode1
Artistic Style Transfer with Internal-external Learning and Contrastive LearningCode1
Unbiased Classification through Bias-Contrastive and Bias-Balanced LearningCode1
TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive?Code1
Molecular Contrastive Learning with Chemical Element Knowledge GraphCode1
Directed Graph Contrastive LearningCode1
CRIS: CLIP-Driven Referring Image SegmentationCode1
Similarity Contrastive Estimation for Self-Supervised Soft Contrastive LearningCode1
A Simple Long-Tailed Recognition Baseline via Vision-Language ModelCode1
ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic ArithmeticCode1
ExCon: Explanation-driven Supervised Contrastive Learning for Image ClassificationCode1
A Practical Contrastive Learning Framework for Single-Image Super-ResolutionCode1
Targeted Supervised Contrastive Learning for Long-Tailed RecognitionCode1
Contrastive Object-level Pre-training with Spatial Noise Curriculum LearningCode1
ContIG: Self-supervised Multimodal Contrastive Learning for Medical Imaging with GeneticsCode1
SPCL: A New Framework for Domain Adaptive Semantic Segmentation via Semantic Prototype-based Contrastive LearningCode1
RegionCL: Can Simple Region Swapping Contribute to Contrastive Learning?Code1
Learning Representation for Clustering via Prototype Scattering and Positive SamplingCode1
Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive LearningCode1
The Way to my Heart is through Contrastive Learning: Remote Photoplethysmography from Unlabelled VideoCode1
SAPNet: Segmentation-Aware Progressive Network for Perceptual Contrastive DerainingCode1
Improving Word Translation via Two-Stage Contrastive LearningCode1
Probabilistic Contrastive Learning for Domain AdaptationCode1
The Emergence of Objectness: Learning Zero-Shot Segmentation from VideosCode1
On Representation Knowledge Distillation for Graph Neural NetworksCode1
TaCL: Improving BERT Pre-training with Token-aware Contrastive LearningCode1
Hard Negative Sampling via Regularized Optimal Transport for Contrastive Representation LearningCode1
Callee: Recovering Call Graphs for Binaries with Transfer and Contrastive LearningCode1
When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?Code1
Towards the Generalization of Contrastive Self-Supervised LearningCode1
Improving Contrastive Learning on Imbalanced Seed Data via Open-World SamplingCode1
Self-Supervised Learning Disentangled Group Representation as FeatureCode1
Equivariant Contrastive LearningCode1
FocusFace: Multi-task Contrastive Learning for Masked Face RecognitionCode1
Robust Contrastive Learning Using Negative Samples with Diminished SemanticsCode1
Image Quality Assessment using Contrastive LearningCode1
Contrastive Learning for Neural Topic ModelCode1
Contrastive Neural Processes for Self-Supervised LearningCode1
Multi-view Contrastive Graph ClusteringCode1
CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIPCode1
Text-Based Person Search with Limited DataCode1
Understanding Dimensional Collapse in Contrastive Self-supervised LearningCode1
Virtual Augmentation Supported Contrastive Learning of Sentence RepresentationsCode1
Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word ProblemsCode1
Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic SegmentationCode1
Decoupled Contrastive LearningCode1
MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase ExtractionCode1
Contrastive Learning for Representation Degeneration Problem in Sequential RecommendationCode1
Weakly Supervised Contrastive LearningCode1
Temperature as Uncertainty in Contrastive LearningCode1
Show:102550
← PrevPage 30 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