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 5501–5525 of 6661 papers

TitleStatusHype
Self-supervised Graph Learning for Occasional Group Recommendation—0
A Multi-Strategy based Pre-Training Method for Cold-Start Recommendation—0
Mind Your Clever Neighbours: Unsupervised Person Re-identification via Adaptive Clustering Relationship Modeling—0
Emotions are Subtle: Learning Sentiment Based Text Representations Using Contrastive Learning—0
Contrastive Cross-domain Recommendation in MatchingCode1
CO2Sum:Contrastive Learning for Factual-Consistent Abstractive Summarization—0
Probabilistic Contrastive Loss for Self-Supervised Learning—0
Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label ClassificationCode1
Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation—0
Contrastive Instance Association for 4D Panoptic Segmentation using Sequences of 3D LiDAR ScansCode0
Contrastive Learning of Sentence Representations—0
CLAWS: Contrastive Learning with hard Attention and Weak Supervision—0
Total-Body Low-Dose CT Image Denoising using Prior Knowledge Transfer Technique with Contrastive Regularization Mechanism—0
Weakly-Supervised Video Object Grounding via Causal Intervention—0
Molecular Contrastive Learning with Chemical Element Knowledge GraphCode1
GANORCON: Are Generative Models Useful for Few-shot Segmentation?—0
Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-IdentificationCode0
Unbiased Classification through Bias-Contrastive and Bias-Balanced LearningCode1
Artistic Style Transfer with Internal-external Learning and Contrastive LearningCode1
Disentangled Contrastive Learning on Graphs—0
Directed Graph Contrastive LearningCode1
TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive?Code1
Compressed Video Contrastive Learning—0
Contrastive Learning of Global and Local Video Representations—0
Looking Beyond Single Images for Contrastive Semantic Segmentation Learning—0
Show:102550
← PrevPage 221 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