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 6101–6150 of 6661 papers

TitleStatusHype
Semi-supervised Contrastive Learning with Similarity Co-calibration—0
Momentum Contrastive Voxel-wise Representation Learning for Semi-supervised Volumetric Medical Image Segmentation—0
Video Corpus Moment Retrieval with Contrastive LearningCode1
Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency—0
Unsupervised Hashing with Contrastive Information BottleneckCode1
PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive LearningCode1
Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation LearningCode1
When Does Contrastive Visual Representation Learning Work?—0
Graph Consistency Based Mean-Teaching for Unsupervised Domain Adaptive Person Re-IdentificationCode0
Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions—0
Contrastive Attraction and Contrastive Repulsion for Representation LearningCode0
Multimodal and Contrastive Learning for Click Fraud Detection—0
Video Class Agnostic Segmentation with Contrastive Learning for Autonomous DrivingCode1
Exploring Instance Relations for Unsupervised Feature EmbeddingCode0
ConCAD: Contrastive Learning-based Cross Attention for Sleep Apnea Detection—0
Contrastive Learning for Unsupervised Image-to-Image Translation—0
Towards Self-Supervision for Video Identification of Individual Holstein-Friesian Cattle: The Cows2021 DatasetCode1
Self-Supervised Learning from Automatically Separated Sound ScenesCode1
MiCE: Mixture of Contrastive Experts for Unsupervised Image ClusteringCode1
Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation—0
Graph Pooling via Coarsened Graph InfomaxCode0
RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning—0
Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive LearningCode1
CoCon: Cooperative-Contrastive LearningCode1
3D Human Action Representation Learning via Cross-View Consistency PursuitCode1
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual RepresentationsCode0
Entailment as Few-Shot LearnerCode1
Improving BERT Model Using Contrastive Learning for Biomedical Relation ExtractionCode1
A Note on Connecting Barlow Twins with Negative-Sample-Free Contrastive LearningCode1
Shot Contrastive Self-Supervised Learning for Scene Boundary Detection—0
Self-supervised Spatial Reasoning on Multi-View Line DrawingsCode1
Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory BankCode1
Multimodal Clustering Networks for Self-supervised Learning from Unlabeled VideosCode1
Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data—0
Mutual Contrastive Learning for Visual Representation LearningCode1
Learning Latent Graph Dynamics for Visual Manipulation of Deformable Objects—0
DeepfakeUCL: Deepfake Detection via Unsupervised Contrastive Learning—0
Pri3D: Can 3D Priors Help 2D Representation Learning?Code1
Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning—0
Distilling Audio-Visual Knowledge by Compositional Contrastive LearningCode1
3KG: Contrastive Learning of 12-Lead Electrocardiograms using Physiologically-Inspired Augmentations—0
IB-DRR: Incremental Learning with Information-Back Discrete Representation Replay—0
SelfReg: Self-supervised Contrastive Regularization for Domain GeneralizationCode1
A Framework using Contrastive Learning for Classification with Noisy Labels—0
Understanding Chinese Video and Language via Contrastive Multimodal Pre-Training—0
Contrastive Learning for Compact Single Image DehazingCode1
DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive LearningCode1
Self-Supervised WiFi-Based Activity Recognition—0
Contrastive Learning Improves Model Robustness Under Label NoiseCode1
Contrastive Out-of-Distribution Detection for Pretrained TransformersCode1
Show:102550
← PrevPage 123 of 134Next →
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