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 17011725 of 6661 papers

TitleStatusHype
Decoupled Contrastive Learning for Long-Tailed RecognitionCode1
MA-GCL: Model Augmentation Tricks for Graph Contrastive LearningCode1
Data Poisoning based Backdoor Attacks to Contrastive LearningCode1
Manifold DivideMix: A Semi-Supervised Contrastive Learning Framework for Severe Label NoiseCode1
Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial RobustnessCode1
SLICER: Learning universal audio representations using low-resource self-supervised pre-trainingCode1
Discriminative and Consistent Representation DistillationCode1
Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural NetworksCode1
SMiLE: Schema-augmented Multi-level Contrastive Learning for Knowledge Graph Link PredictionCode1
MABEL: Attenuating Gender Bias using Textual Entailment DataCode1
ISD: Self-Supervised Learning by Iterative Similarity DistillationCode1
Joint Generative and Contrastive Learning for Unsupervised Person Re-identificationCode1
Decoupled Contrastive LearningCode1
DC-Seg: Disentangled Contrastive Learning for Brain Tumor Segmentation with Missing ModalitiesCode1
Contrastive Pretraining for Echocardiography Segmentation with Limited DataCode1
Soft Contrastive Learning for Visual LocalizationCode1
Is Contrastive Learning Necessary? A Study of Data Augmentation vs Contrastive Learning in Sequential RecommendationCode1
Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical ImagingCode1
ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic SegmentationCode1
Joint Contrastive Learning with Infinite PossibilitiesCode1
Debiased Contrastive LearningCode1
Debiased Contrastive Learning for Sequential RecommendationCode1
CLCC: Contrastive Learning for Color ConstancyCode1
Jigsaw Clustering for Unsupervised Visual Representation LearningCode1
Community-Invariant Graph Contrastive LearningCode1
Show:102550
← PrevPage 69 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