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 4226–4250 of 6661 papers

TitleStatusHype
Contrastive ground-level image and remote sensing pre-training improves representation learning for natural world imagery—0
Contrastive Hierarchical Discourse Graph for Scientific Document Summarization—0
Contrastive Label Enhancement—0
Contrastive Language-Action Pre-training for Temporal Localization—0
Bridging Text and Crystal Structures: Literature-driven Contrastive Learning for Materials Science—0
Contrastive Language Video Time Pre-training—0
Contrastive Learning and Cycle Consistency-based Transductive Transfer Learning for Target Annotation—0
Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation—0
Contrastive Learning and the Emergence of Attributes Associations—0
CONSS: Contrastive Learning Approach for Semi-Supervised Seismic Facies Classification—0
Contrastive Learning as Goal-Conditioned Reinforcement Learning—0
Contrastive Learning as Kernel Approximation—0
Contrastive learning-based agent modeling for deep reinforcement learning—0
Contrastive Learning based Deep Latent Masking for Music Source Separation—0
Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification—0
Contrastive learning-based pretraining improves representation and transferability of diabetic retinopathy classification models—0
Contrastive Learning Based Recursive Dynamic Multi-Scale Network for Image Deraining—0
Contrastive Learning-Based Spectral Knowledge Distillation for Multi-Modality and Missing Modality Scenarios in Semantic Segmentation—0
Contrastive Learning-based User Identification with Limited Data on Smart Textiles—0
Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions—0
Contrastive Learning-Enhanced Nearest Neighbor Mechanism for Multi-Label Text Classification—0
Contrastive Learning-Enhanced Trajectory Matching for Small-Scale Dataset Distillation—0
Contrastive Learning for Automotive mmWave Radar Detection Points Based Instance Segmentation—0
Contrastive Learning for Climate Model Bias Correction and Super-Resolution—0
Contrastive Learning for Cold Start Recommendation with Adaptive Feature Fusion—0
Show:102550
← PrevPage 170 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