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

Showing 12261250 of 6661 papers

TitleStatusHype
D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance AnnotationCode1
Automated Spatio-Temporal Graph Contrastive LearningCode1
GTC: GNN-Transformer Co-contrastive Learning for Self-supervised Heterogeneous Graph RepresentationCode1
H2CGL: Modeling Dynamics of Citation Network for Impact PredictionCode1
Big Self-Supervised Models Advance Medical Image ClassificationCode1
BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine TranslationCode1
Data Augmenting Contrastive Learning of Speech Representations in the Time DomainCode1
AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative AdversariesCode1
Contrastive Laplacian EigenmapsCode1
Contrastive Pretraining for Echocardiography Segmentation with Limited DataCode1
ISD: Self-Supervised Learning by Iterative Similarity DistillationCode1
Jigsaw Clustering for Unsupervised Visual Representation LearningCode1
Replication: Contrastive Learning and Data Augmentation in Traffic Classification Using a Flowpic Input RepresentationCode1
ConDA: Contrastive Domain Adaptation for AI-generated Text DetectionCode1
Contrastive Learning and Mixture of Experts Enables Precise Vector EmbeddingsCode1
Data Poisoning Attacks Against Multimodal EncodersCode1
Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport DistillationCode1
GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D UnderstandingCode1
Joint Learning of Localized Representations from Medical Images and ReportsCode1
GraSS: Contrastive Learning with Gradient Guided Sampling Strategy for Remote Sensing Image Semantic SegmentationCode1
Alleviating Exposure Bias via Contrastive Learning for Abstractive Text SummarizationCode1
Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical ImagingCode1
Debiased Contrastive Learning for Sequential RecommendationCode1
A Unified Generative Framework for Realistic Lidar Simulation in Autonomous Driving SystemsCode1
GRENADE: Graph-Centric Language Model for Self-Supervised Representation Learning on Text-Attributed GraphsCode1
Show:102550
← PrevPage 50 of 267Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6Unverified
2ResNet50ImageNet Top-1 Accuracy73Unverified
3ResNet50ImageNet Top-1 Accuracy71.1Unverified
4ResNet50ImageNet Top-1 Accuracy69.3Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8Unverified
7ResNet50ImageNet Top-1 Accuracy63.6Unverified
8ResNet50ImageNet Top-1 Accuracy61.5Unverified
9ResNet50ImageNet Top-1 Accuracy61.5Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55Unverified