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 6376–6400 of 6661 papers

TitleStatusHype
Self-Supervised Relationship Probing—0
Self-Supervised Representation Learning for Nerve Fiber Distribution Patterns in 3D-PLI—0
Self-supervised Representation Learning for Trip Recommendation—0
Self-Supervised Representation Learning from Arbitrary Scenarios—0
Self-supervised Representation Learning on Electronic Health Records with Graph Kernel Infomax—0
Self-supervised representation learning via adaptive hard-positive mining—0
Self-Supervised Representation Learning via Latent Graph Prediction—0
Self-Supervised Representation Learning With MUlti-Segmental Informational Coding (MUSIC)—0
Self-Supervised Representation Learning with Cross-Context Learning between Global and Hypercolumn Features—0
SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking—0
SAIL: Self-Augmented Graph Contrastive Learning—0
Self-supervised Speaker Recognition Training Using Human-Machine Dialogues—0
Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularization—0
Self-supervised Temporal Learning—0
Self-Supervised Time-Series Anomaly Detection Using Learnable Data Augmentation—0
Self-Supervised Training of Speaker Encoder with Multi-Modal Diverse Positive Pairs—0
Self-supervised Transformer for Deepfake Detection—0
Latent Spatiotemporal Adaptation for Generalized Face Forgery Video Detection—0
Self-supervised Video-centralised Transformer for Video Face Clustering—0
Self-Supervised Video GANs: Learning for Appearance Consistency and Motion Coherency—0
Self-supervised video pretraining yields robust and more human-aligned visual representations—0
Self-Supervised Video Representation Learning with Motion-Contrastive Perception—0
Self-Supervised Video Representation Learning via Latent Time Navigation—0
Self-Supervised Video Representation Learning in a Heuristic Decoupled Perspective—0
Self-Supervised Video Representation Learning with Meta-Contrastive Network—0
Show:102550
← PrevPage 256 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