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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 6126–6150 of 6661 papers

Title	Date	Tasks	Status	Hype
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations	Apr 29, 2021	Contrastive LearningFine-Grained Image Classification	CodeCode Available	0
Entailment as Few-Shot Learner	Apr 29, 2021	Contrastive LearningData Augmentation	CodeCode Available	1
Improving BERT Model Using Contrastive Learning for Biomedical Relation Extraction	Apr 28, 2021	Contrastive LearningData Augmentation	CodeCode Available	1
A Note on Connecting Barlow Twins with Negative-Sample-Free Contrastive Learning	Apr 28, 2021	Contrastive LearningSelf-Supervised Learning	CodeCode Available	1
Shot Contrastive Self-Supervised Learning for Scene Boundary Detection	Apr 28, 2021	Boundary DetectionContrastive Learning	—Unverified	0
Self-supervised Spatial Reasoning on Multi-View Line Drawings	Apr 27, 2021	Binary ClassificationContrastive Learning	CodeCode Available	1
Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank	Apr 27, 2021	Contrastive LearningDomain Adaptation	CodeCode Available	1
Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos	Apr 26, 2021	Action LocalizationClustering	CodeCode Available	1
Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data	Apr 26, 2021	Contrastive LearningRepresentation Learning	—Unverified	0
Mutual Contrastive Learning for Visual Representation Learning	Apr 26, 2021	Contrastive LearningFew-Shot Learning	CodeCode Available	1
Learning Latent Graph Dynamics for Visual Manipulation of Deformable Objects	Apr 25, 2021	Contrastive LearningDeformable Object Manipulation	—Unverified	0
DeepfakeUCL: Deepfake Detection via Unsupervised Contrastive Learning	Apr 23, 2021	Contrastive LearningDeepFake Detection	—Unverified	0
Pri3D: Can 3D Priors Help 2D Representation Learning?	Apr 22, 2021	Contrastive LearningInstance Segmentation	CodeCode Available	1
Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning	Apr 22, 2021	Contrastive LearningDomain Adaptation	—Unverified	0
Distilling Audio-Visual Knowledge by Compositional Contrastive Learning	Apr 22, 2021	Audio Taggingaudio-visual learning	CodeCode Available	1
3KG: Contrastive Learning of 12-Lead Electrocardiograms using Physiologically-Inspired Augmentations	Apr 21, 2021	Contrastive LearningRhythm	—Unverified	0
IB-DRR: Incremental Learning with Information-Back Discrete Representation Replay	Apr 21, 2021	Contrastive LearningIncremental Learning	—Unverified	0
SelfReg: Self-supervised Contrastive Regularization for Domain Generalization	Apr 20, 2021	Contrastive LearningDomain Generalization	CodeCode Available	1
A Framework using Contrastive Learning for Classification with Noisy Labels	Apr 19, 2021	Contrastive LearningGeneral Classification	—Unverified	0
Understanding Chinese Video and Language via Contrastive Multimodal Pre-Training	Apr 19, 2021	Contrastive LearningLanguage Modeling	—Unverified	0
Contrastive Learning for Compact Single Image Dehazing	Apr 19, 2021	Contrastive LearningImage Dehazing	CodeCode Available	1
DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning	Apr 19, 2021	Contrastive LearningRepresentation Learning	CodeCode Available	1
Self-Supervised WiFi-Based Activity Recognition	Apr 19, 2021	Activity RecognitionContrastive Learning	—Unverified	0
Contrastive Learning Improves Model Robustness Under Label Noise	Apr 19, 2021	Contrastive Learningimage-classification	CodeCode Available	1
Contrastive Out-of-Distribution Detection for Pretrained Transformers	Apr 18, 2021	Contrastive LearningOut-of-Distribution Detection	CodeCode Available	1

Show:10 25 50

← PrevPage 246 of 267Next →

All datasets imagenet-1k 10,000 People - Human Pose Recognition Data CIFAR-10 STL-10

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	ResNet50	ImageNet Top-1 Accuracy	73.6	—	Unverified
2	ResNet50	ImageNet Top-1 Accuracy	73	—	Unverified
3	ResNet50	ImageNet Top-1 Accuracy	71.1	—	Unverified
4	ResNet50	ImageNet Top-1 Accuracy	69.3	—	Unverified
5	ResNet50 (v2)	ImageNet Top-1 Accuracy	67.6	—	Unverified
6	ResNet50 (v2)	ImageNet Top-1 Accuracy	63.8	—	Unverified
7	ResNet50	ImageNet Top-1 Accuracy	63.6	—	Unverified
8	ResNet50	ImageNet Top-1 Accuracy	61.5	—	Unverified
9	ResNet50	ImageNet Top-1 Accuracy	61.5	—	Unverified
10	ResNet50 (4×)	ImageNet Top-1 Accuracy	61.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	1	0..5sec	1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	IPCL (ResNet18)	Accuracy (Top-1)	84.77	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	IPCL (ResNet18)	Accuracy (Top-1)	85.55	—	Unverified