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 1576–1600 of 6661 papers

Title	Date	Tasks	Status	Hype
OODformer: Out-Of-Distribution Detection Transformer	Jul 19, 2021	Contrastive Learningimage-classification	CodeCode Available	1
Separating Skills and Concepts for Novel Visual Question Answering	Jul 19, 2021	AttributeContrastive Learning	CodeCode Available	1
Lesion-based Contrastive Learning for Diabetic Retinopathy Grading from Fundus Images	Jul 17, 2021	Contrastive LearningData Augmentation	CodeCode Available	1
Self-supervised Representation Learning Framework for Remote Physiological Measurement Using Spatiotemporal Augmentation Loss	Jul 16, 2021	Contrastive LearningData Augmentation	CodeCode Available	1
More Robust Dense Retrieval with Contrastive Dual Learning	Jul 16, 2021	Contrastive LearningInformation Retrieval	CodeCode Available	1
Anatomy-Constrained Contrastive Learning for Synthetic Segmentation without Ground-truth	Jul 12, 2021	AnatomyContrastive Learning	CodeCode Available	1
Contrastive Learning for Cold-Start Recommendation	Jul 12, 2021	Contrastive LearningRecommendation Systems	CodeCode Available	1
A Hierarchical Dual Model of Environment- and Place-Specific Utility for Visual Place Recognition	Jul 6, 2021	Contrastive LearningImage Retrieval	CodeCode Available	1
Contrastive Multimodal Fusion with TupleInfoNCE	Jul 6, 2021	Contrastive LearningRepresentation Learning	CodeCode Available	1
Improving Text-to-Image Synthesis Using Contrastive Learning	Jul 6, 2021	Contrastive LearningImage Generation	CodeCode Available	1
Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation	Jul 5, 2021	Contrastive LearningDomain Adaptation	CodeCode Available	1
Bag of Instances Aggregation Boosts Self-supervised Distillation	Jul 4, 2021	Contrastive LearningLinear evaluation	CodeCode Available	1
Simpler, Faster, Stronger: Breaking The log-K Curse On Contrastive Learners With FlatNCE	Jul 2, 2021	Contrastive Learning	CodeCode Available	1
CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understanding	Jul 1, 2021	Contrastive LearningNatural Language Understanding	CodeCode Available	1
OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Data	Jun 29, 2021	Contrastive LearningRepresentation Learning	CodeCode Available	1
Self-Contrastive Learning: Single-viewed Supervised Contrastive Framework using Sub-network	Jun 29, 2021	Contrastive Learning	CodeCode Available	1
Co^2L: Contrastive Continual Learning	Jun 28, 2021	Continual LearningContrastive Learning	CodeCode Available	1
UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning	Jun 26, 2021	Contrastive LearningDiversity	CodeCode Available	1
Time-Series Representation Learning via Temporal and Contextual Contrasting	Jun 26, 2021	Automatic Sleep Stage ClassificationContrastive Learning	CodeCode Available	1
Winning the CVPR'2021 Kinetics-GEBD Challenge: Contrastive Learning Approach	Jun 22, 2021	Boundary DetectionContrastive Learning	CodeCode Available	1
VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning	Jun 21, 2021	Action ClassificationAction Recognition	CodeCode Available	1
Can contrastive learning avoid shortcut solutions?	Jun 21, 2021	Contrastive Learning	CodeCode Available	1
Multi-level Feature Learning for Contrastive Multi-view Clustering	Jun 21, 2021	ClusteringContrastive Learning	CodeCode Available	1
Underwater Image Restoration via Contrastive Learning and a Real-world Dataset	Jun 20, 2021	BenchmarkingContrastive Learning	CodeCode Available	1
Neighborhood Contrastive Learning for Novel Class Discovery	Jun 20, 2021	ClusteringContrastive Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 64 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