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 751–800 of 6661 papers

TitleStatusHype
Contrastive Learning with Adversarial Perturbations for Conditional Text GenerationCode1
CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIPCode1
DyTed: Disentangled Representation Learning for Discrete-time Dynamic GraphCode1
Capsule Network based Contrastive Learning of Unsupervised Visual RepresentationsCode1
BECLR: Batch Enhanced Contrastive Few-Shot LearningCode1
Contrastive Learning with Bidirectional Transformers for Sequential RecommendationCode1
CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly DetectionCode1
Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity RecognitionCode1
A Comparative Study of Pre-trained Encoders for Low-Resource Named Entity RecognitionCode1
Edge Guided GANs with Contrastive Learning for Semantic Image SynthesisCode1
CaseGNN++: Graph Contrastive Learning for Legal Case Retrieval with Graph AugmentationCode1
Effective Conditioned and Composed Image Retrieval Combining CLIP-Based FeaturesCode1
Efficient Contrastive Learning via Novel Data Augmentation and Curriculum LearningCode1
Efficient fine-tuning methodology of text embedding models for information retrieval: contrastive learning penalty (clp)Code1
Category Contrast for Unsupervised Domain Adaptation in Visual TasksCode1
Efficient Medical Vision-Language Alignment Through Adapting Masked Vision ModelsCode1
Contrastive Learning with Synthetic PositivesCode1
Empowering Collaborative Filtering with Principled Adversarial Contrastive LossCode1
A Reference-less Quality Metric for Automatic Speech Recognition via Contrastive-Learning of a Multi-Language Model with Self-SupervisionCode1
End-to-end training of Multimodal Model and ranking ModelCode1
Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMsCode1
Normality Learning-based Graph Anomaly Detection via Multi-Scale Contrastive LearningCode1
A Review-aware Graph Contrastive Learning Framework for RecommendationCode1
Contrastive Learning of User Behavior Sequence for Context-Aware Document RankingCode1
Contrastive Learning of Sentence Embeddings from ScratchCode1
Contrastive Learning Reduces Hallucination in ConversationsCode1
CLASP: Contrastive Language-Speech Pretraining for Multilingual Multimodal Information RetrievalCode1
Enhancing Modal Fusion by Alignment and Label Matching for Multimodal Emotion RecognitionCode1
Enhancing Representation in Radiography-Reports Foundation Model: A Granular Alignment Algorithm Using Masked Contrastive LearningCode1
Enhancing Self-supervised Video Representation Learning via Multi-level Feature OptimizationCode1
Enhancing Sound Source Localization via False Negative EliminationCode1
Enriched Music Representations with Multiple Cross-modal Contrastive LearningCode1
BCE-Net: Reliable Building Footprints Change Extraction based on Historical Map and Up-to-Date Images using Contrastive LearningCode1
Adversarial Self-Supervised Contrastive LearningCode1
Cluster-Level Contrastive Learning for Emotion Recognition in ConversationsCode1
Equivariant Contrastive LearningCode1
3D Interaction Geometric Pre-training for Molecular Relational LearningCode1
Cluster-guided Contrastive Graph Clustering NetworkCode1
Certifiably Robust Graph Contrastive LearningCode1
Artistic Style Transfer with Internal-external Learning and Contrastive LearningCode1
CETN: Contrast-enhanced Through Network for CTR PredictionCode1
ArtNeRF: A Stylized Neural Field for 3D-Aware Cartoonized Face SynthesisCode1
Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World AttacksCode1
EViT: Privacy-Preserving Image Retrieval via Encrypted Vision Transformer in Cloud ComputingCode1
Contrastive Learning of Musical RepresentationsCode1
Expectation-Maximization Contrastive Learning for Compact Video-and-Language RepresentationsCode1
Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive LearningCode1
Explanation Guided Contrastive Learning for Sequential RecommendationCode1
Contrastive learning of global and local features for medical image segmentation with limited annotationsCode1
A Broad Study on the Transferability of Visual Representations with Contrastive LearningCode1
Show:102550
← PrevPage 16 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