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 1601–1625 of 6661 papers

Title	Date	Tasks	Status	Hype
TS2Vec: Towards Universal Representation of Time Series	Jun 19, 2021	Anomaly DetectionContrastive Learning	CodeCode Available	1
Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation	Jun 18, 2021	Contrastive LearningDomain Adaptation	CodeCode Available	1
Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting	Jun 18, 2021	Action RecognitionAction Recognition In Videos	CodeCode Available	1
Contrastive Learning of Generalized Game Representations	Jun 18, 2021	Contrastive LearningImage Classification	CodeCode Available	1
A Self-supervised Method for Entity Alignment	Jun 17, 2021	Contrastive LearningEntity Alignment	CodeCode Available	1
Prototypical Graph Contrastive Learning	Jun 17, 2021	ClusteringContrastive Learning	CodeCode Available	1
Poisoning and Backdooring Contrastive Learning	Jun 17, 2021	Contrastive Learning	CodeCode Available	1
Contrastive Learning with Continuous Proxy Meta-Data for 3D MRI Classification	Jun 16, 2021	Alzheimer's DetectionContrastive Learning	CodeCode Available	1
Positional Contrastive Learning for Volumetric Medical Image Segmentation	Jun 16, 2021	Contrastive Learningimage-classification	CodeCode Available	1
Evaluating Modules in Graph Contrastive Learning	Jun 15, 2021	Contrastive LearningGraph Classification	CodeCode Available	1
Biomedical Entity Linking with Contrastive Context Matching	Jun 14, 2021	ArticlesContrastive Learning	CodeCode Available	1
Hybrid Generative-Contrastive Representation Learning	Jun 11, 2021	Contrastive LearningDecoder	CodeCode Available	1
Graph Contrastive Learning Automated	Jun 10, 2021	Contrastive LearningRepresentation Learning	CodeCode Available	1
Adversarial Graph Augmentation to Improve Graph Contrastive Learning	Jun 10, 2021	Contrastive LearningSelf-Supervised Learning	CodeCode Available	1
PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive Learning	Jun 10, 2021	3D Hand Pose EstimationContrastive Learning	CodeCode Available	1
Neighborhood Contrastive Learning Applied to Online Patient Monitoring	Jun 9, 2021	BIG-bench Machine LearningContrastive Learning	CodeCode Available	1
CLCC: Contrastive Learning for Color Constancy	Jun 9, 2021	Color ConstancyContrastive Learning	CodeCode Available	1
Pretrained Encoders are All You Need	Jun 9, 2021	AllContrastive Learning	CodeCode Available	1
Learning Markov State Abstractions for Deep Reinforcement Learning	Jun 8, 2021	continuous-controlContinuous Control	CodeCode Available	1
Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss	Jun 8, 2021	Contrastive LearningGeneralization Bounds	CodeCode Available	1
Mean-Shifted Contrastive Loss for Anomaly Detection	Jun 7, 2021	Anomaly DetectionContrastive Learning	CodeCode Available	1
Self-Damaging Contrastive Learning	Jun 6, 2021	Contrastive LearningLinear evaluation	CodeCode Available	1
Category Contrast for Unsupervised Domain Adaptation in Visual Tasks	Jun 5, 2021	Contrastive LearningDomain Adaptation	CodeCode Available	1
MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph	Jun 5, 2021	Contrastive LearningRepresentation Learning	CodeCode Available	1
Aligning Pretraining for Detection via Object-Level Contrastive Learning	Jun 4, 2021	Contrastive LearningObject	CodeCode Available	1

Show:10 25 50

← PrevPage 65 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