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 2226–2250 of 6661 papers

TitleStatusHype
CLICv2: Image Complexity Representation via Content Invariance Contrastive Learning—0
DeepfakeUCL: Deepfake Detection via Unsupervised Contrastive Learning—0
Click-through Rate Prediction with Auto-Quantized Contrastive Learning—0
A Survey on Bridging EEG Signals and Generative AI: From Image and Text to Beyond—0
Deep Contrastive Multi-view Clustering under Semantic Feature Guidance—0
Understanding Deep Contrastive Learning via Coordinate-wise Optimization—0
A Survey of Learning on Small Data: Generalization, Optimization, and Challenge—0
Deep Contrastive Multiview Network Embedding—0
Deep Contrastive Learning for Feature Alignment: Insights from Housing-Household Relationship Inference—0
A Survey of Deep Learning-based Radiology Report Generation Using Multimodal Data—0
Deep Contrastive Graph Representation via Adaptive Homotopy Learning—0
Deep Contrastive Graph Learning with Clustering-Oriented Guidance—0
CLGNN: A Contrastive Learning-based GNN Model for Betweenness Centrality Prediction on Temporal Graphs—0
AGPNet -- Autonomous Grading Policy Network—0
Deep Continuous Prompt for Contrastive Learning of Sentence Embeddings—0
CL-Flow:Strengthening the Normalizing Flows by Contrastive Learning for Better Anomaly Detection—0
Deep Code Search with Naming-Agnostic Contrastive Multi-View Learning—0
CLExtract: Recovering Highly Corrupted DVB/GSE Satellite Stream with Contrastive Learning—0
A Co-training Approach for Noisy Time Series Learning—0
Gaussian Graph with Prototypical Contrastive Learning in E-Commerce Bundle Recommendation—0
Gaze Estimation with Eye Region Segmentation and Self-Supervised Multistream Learning—0
GCL: Gradient-Guided Contrastive Learning for Medical Image Segmentation with Multi-Perspective Meta Labels—0
Deep Clustering by Semantic Contrastive Learning—0
DeepCluE: Enhanced Image Clustering via Multi-layer Ensembles in Deep Neural Networks—0
CLERF: Contrastive LEaRning for Full Range Head Pose Estimation—0
Show:102550
← PrevPage 90 of 267Next →
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