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 3526–3550 of 6661 papers

TitleStatusHype
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 142 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