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 1561–1570 of 6661 papers

Title	Date	Tasks	Status	Hype
Counterfactual contrastive learning: robust representations via causal image synthesis	Mar 14, 2024	Contrastive Learningcounterfactual	CodeCode Available	1
NCAGC: A Neighborhood Contrast Framework for Attributed Graph Clustering	Jun 16, 2022	ClusteringContrastive Learning	CodeCode Available	1
Dual Contrastive Prediction for Incomplete Multi-view Representation Learning	Apr 1, 2023	Action RecognitionContrastive Learning	CodeCode Available	1
Dual-stream Feature Augmentation for Domain Generalization	Sep 7, 2024	Contrastive LearningDomain Generalization	CodeCode Available	1
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning	Feb 20, 2021	Adversarial AttackAdversarial Robustness	CodeCode Available	1
On Isotropy, Contextualization and Learning Dynamics of Contrastive-based Sentence Representation Learning	Dec 18, 2022	Contrastive LearningRepresentation Learning	CodeCode Available	1
CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation	Mar 22, 2022	Contrastive LearningRepresentation Learning	CodeCode Available	1
CDPAM: Contrastive learning for perceptual audio similarity	Feb 9, 2021	Contrastive LearningSpeech Enhancement	CodeCode Available	1
Adversarial Self-Supervised Contrastive Learning	Jun 13, 2020	Adversarial AttackContrastive Learning	CodeCode Available	1
DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing	Sep 22, 2021	AttributeContrastive Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 157 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