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 6526–6550 of 6661 papers

TitleStatusHype
Self-supervised Video Representation Learning Using Inter-intra Contrastive FrameworkCode1
Contrastive Variational Reinforcement Learning for Complex ObservationsCode1
Data Cleansing with Contrastive Learning for Vocal Note Event AnnotationsCode0
Temporal Context Aggregation for Video Retrieval with Contrastive LearningCode1
LoCo: Local Contrastive Representation Learning—0
SeCo: Exploring Sequence Supervision for Unsupervised Representation LearningCode1
A Visual Analytics Framework for Reviewing Multivariate Time-Series Data with Dimensionality Reduction—0
Contrastive Learning for Unpaired Image-to-Image TranslationCode2
Distilling Visual Priors from Self-Supervised LearningCode1
Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action RecognitionCode1
A Visual Analytics Framework for Contrastive Network Analysis—0
On Learning Universal Representations Across Languages—0
Contrastive Learning for Unpaired Image-to-Image TranslationCode1
Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction—0
Self-Supervised Contrastive Learning for Unsupervised Phoneme SegmentationCode1
K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations—0
3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised LearningCode1
Contrastive Visual-Linguistic PretrainingCode0
Gradient Regularized Contrastive Learning for Continual Domain Adaptation—0
Augmentation adversarial training for self-supervised speaker recognition—0
Few-shot Visual Reasoning with Meta-analogical Contrastive Learning—0
Hierarchical Contrastive Motion Learning for Video Action Recognition—0
Hybrid Discriminative-Generative Training via Contrastive LearningCode1
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted InstancesCode1
GraphCL: Contrastive Self-Supervised Learning of Graph Representations—0
Show:102550
← PrevPage 262 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