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 3501–3550 of 6661 papers

TitleStatusHype
Multi-hop Commonsense Knowledge Injection Framework for Zero-Shot Commonsense Question Answering—0
Exploiting Pseudo Image Captions for Multimodal Summarization—0
Traffic Forecasting on New Roads Using Spatial Contrastive Pre-Training (SCPT)Code0
Alleviating Over-smoothing for Unsupervised Sentence RepresentationCode1
Region-based Contrastive Pretraining for Medical Image Retrieval with Anatomic Query—0
MSVQ: Self-Supervised Learning with Multiple Sample Views and QueuesCode0
Behavior Contrastive Learning for Unsupervised Skill DiscoveryCode1
CSGCL: Community-Strength-Enhanced Graph Contrastive LearningCode1
SEGA: Structural Entropy Guided Anchor View for Graph Contrastive LearningCode0
DEnsity: Open-domain Dialogue Evaluation Metric using Density EstimationCode1
Graph Masked Autoencoder for Sequential RecommendationCode1
Cone: Unsupervised Contrastive Opinion ExtractionCode0
Vision Language Pre-training by Contrastive Learning with Cross-Modal Similarity Regulation—0
Model-Contrastive Federated Domain Adaptation—0
Contrastive Enhanced Slide Filter Mixer for Sequential RecommendationCode0
Unlocking the Power of Open Set : A New Perspective for Open-Set Noisy Label Learning—0
Visual Causal Scene Refinement for Video Question AnsweringCode3
Dual Degradation Representation for Joint Deraining and Low-Light Enhancement in the DarkCode0
Weighted Point Cloud Normal Estimation—0
Keyword-Based Diverse Image Retrieval by Semantics-aware Contrastive Learning and Transformer—0
Automated Spatio-Temporal Graph Contrastive LearningCode1
Deep Unsupervised Learning for 3D ALS Point Cloud Change DetectionCode0
REINFOREST: Reinforcing Semantic Code Similarity for Cross-Lingual Code Search ModelsCode0
AmGCL: Feature Imputation of Attribute Missing Graph via Self-supervised Contrastive Learning—0
Contrastive Graph Clustering in Curvature Spaces—0
HD2Reg: Hierarchical Descriptors and Detectors for Point Cloud RegistrationCode1
Contrastive Learning for Sleep Staging based on Inter Subject CorrelationCode0
A vector quantized masked autoencoder for audiovisual speech emotion recognition—0
Contrastive Learning for Low-light Raw Denoising—0
Knowledge graph-enhanced molecular contrastive learning with functional prompt—0
Contrastive Mean Teacher for Domain Adaptive Object DetectorsCode1
Multi-Domain Learning From Insufficient Annotations—0
Disentangled Contrastive Collaborative FilteringCode1
Multi-Modality Deep Network for JPEG Artifacts Reduction—0
Revisiting Graph Contrastive Learning for Anomaly DetectionCode0
Forward-Forward Contrastive Learning—0
Using Spatio-Temporal Dual-Stream Network with Self-Supervised Learning for Lung Tumor Classification on Radial Probe Endobronchial Ultrasound Video—0
FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction—0
Alleviating Exposure Bias via Multi-level Contrastive Learning and Deviation Simulation in Abstractive SummarizationCode0
Denoising Multi-modal Sequential Recommenders with Contrastive Learning—0
Cross-Stream Contrastive Learning for Self-Supervised Skeleton-Based Action Recognition—0
Improving Contrastive Learning of Sentence Embeddings from AI FeedbackCode1
Topic Shift Detection in Chinese Dialogues: Corpus and Benchmark—0
Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth LabelsCode1
CLIP-S^4: Language-Guided Self-Supervised Semantic Segmentation—0
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual RepresentationsCode1
Part Aware Contrastive Learning for Self-Supervised Action RecognitionCode1
What Do Self-Supervised Vision Transformers Learn?Code1
A Simplified Framework for Contrastive Learning for Node Representations—0
Tracing Knowledge Instead of Paterns: Stable Knowledge Tracing with Diagnostic TransformerCode1
Show:102550
← PrevPage 71 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