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 1841–1850 of 6661 papers

Title	Date	Tasks	Status	Hype
Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation	Jul 3, 2020	Contrastive LearningKnowledge Distillation	CodeCode Available	1
Data Augmenting Contrastive Learning of Speech Representations in the Time Domain	Jul 2, 2020	Contrastive LearningData Augmentation	CodeCode Available	1
Debiased Contrastive Learning	Jul 1, 2020	Contrastive LearningGeneralization Bounds	CodeCode Available	1
Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval	Jul 1, 2020	Contrastive LearningPassage Retrieval	CodeCode Available	1
Subject-Aware Contrastive Learning for Biosignals	Jun 30, 2020	Anomaly DetectionContrastive Learning	CodeCode Available	1
Video Representation Learning with Visual Tempo Consistency	Jun 28, 2020	Action AnticipationAction Detection	CodeCode Available	1
On Equivariant and Invariant Learning of Object Landmark Representations	Jun 26, 2020	Contrastive LearningObject	CodeCode Available	1
Joint Contrastive Learning for Unsupervised Domain Adaptation	Jun 18, 2020	Contrastive LearningDomain Adaptation	CodeCode Available	1
Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations	Jun 18, 2020	Contrastive Learning	CodeCode Available	1
Contrastive learning of global and local features for medical image segmentation with limited annotations	Jun 18, 2020	Contrastive LearningData Augmentation	CodeCode Available	1

Show:10 25 50

← PrevPage 185 of 667Next →

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