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 5926–5950 of 6661 papers

TitleStatusHype
Knowledge-Rich Self-Supervision for Biomedical Entity Linking—0
Graph Representation Learning via Contrasting Cluster Assignments—0
Gaze Estimation with Eye Region Segmentation and Self-Supervised Multistream Learning—0
Transferrable Contrastive Learning for Visual Domain Adaptation—0
From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model CompressionCode0
Semi-Supervised Contrastive Learning for Remote Sensing: Identifying Ancient Urbanization in the South Central Andes—0
Smooth-Swap: A Simple Enhancement for Face-Swapping with Smoothness—0
Technical Language Supervision for Intelligent Fault Diagnosis in Process Industry—0
A Self-supervised Mixed-curvature Graph Neural Network—0
Tradeoffs Between Contrastive and Supervised Learning: An Empirical Study—0
Dual Cluster Contrastive learning for Object Re-IdentificationCode0
From Good to Best: Two-Stage Training for Cross-lingual Machine Reading Comprehension—0
Contextualized Spatio-Temporal Contrastive Learning with Self-SupervisionCode0
Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework—0
Boosting Contrastive Learning with Relation Knowledge Distillation—0
Contrastive Instruction-Trajectory Learning for Vision-Language NavigationCode0
Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularization—0
Time-Equivariant Contrastive Video Representation Learning—0
Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation LearningCode0
4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding—0
Seeing Objects in dark with Continual Contrastive Learning—0
CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks—0
Self-supervised Graph Learning for Occasional Group Recommendation—0
U2-Former: A Nested U-shaped Transformer for Image Restoration—0
A Multi-Strategy based Pre-Training Method for Cold-Start Recommendation—0
Show:102550
← PrevPage 238 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