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 6126–6150 of 6661 papers

TitleStatusHype
SynCLR: A Synthesis Framework for Contrastive Learning of out-of-domain Speech Representations—0
Self-supervised Learning for Sequential Recommendation with Model Augmentation—0
Interrogating Paradigms in Self-supervised Graph Representation Learning—0
Multi-Domain Self-Supervised Learning—0
MemREIN: Rein the Domain Shift for Cross-Domain Few-Shot Learning—0
Information-Aware Time Series Meta-Contrastive Learning—0
Inductive-Biases for Contrastive Learning of Disentangled Representations—0
Contrastive Learning is Just Meta-Learning—0
ESCo: Towards Provably Effective and Scalable Contrastive Representation Learning—0
Unsupervised Contrastive Learning for Signal-Dependent Noise Synthesis—0
Zero-CL: Instance and Feature decorrelation for negative-free symmetric contrastive learning—0
SimMER: Simple Maximization of Entropy and Rank for Self-supervised Representation Learning—0
Context-invariant, multi-variate time series representations—0
Contrastively Enforcing Distinctiveness for Multi-Label Classification—0
Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling—0
Representation Disentanglement in Generative Models with Contrastive Learning—0
Identity-Disentangled Adversarial Augmentation for Self-supervised Learning—0
Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Id—0
Self-Contrastive Learning—0
Residual Contrastive Learning: Unsupervised Representation Learning from Residuals—0
How does Contrastive Pre-training Connect Disparate Domains?—0
ConFeSS: A Framework for Single Source Cross-Domain Few-Shot Learning—0
Hierarchical Cross Contrastive Learning of Visual Representations—0
Federated Contrastive Learning for Privacy-Preserving Unpaired Image-to-Image Translation—0
Contrastive Video-Language Segmentation—0
Show:102550
← PrevPage 246 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