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 6426–6450 of 6661 papers

Title	Date	Tasks	Status	Hype
Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning	Nov 3, 2020	Contrastive LearningData Augmentation	CodeCode Available	1
Semi-supervised Facial Action Unit Intensity Estimation with Contrastive Learning	Nov 3, 2020	Contrastive LearningUnsupervised Pre-training	—Unverified	0
Learning to Contrast the Counterfactual Samples for Robust Visual Question Answering	Nov 1, 2020	Contrastive Learningcounterfactual	CodeCode Available	1
Distilling Structured Knowledge for Text-Based Relational Reasoning	Nov 1, 2020	Contrastive LearningKnowledge Distillation	—Unverified	0
A Survey on Contrastive Self-supervised Learning	Oct 31, 2020	Action RecognitionContrastive Learning	—Unverified	0
Self-supervised Representation Learning for Evolutionary Neural Architecture Search	Oct 31, 2020	Contrastive LearningGraph Neural Network	CodeCode Available	0
Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information Maximization	Oct 30, 2020	Contrastive LearningGeneral Classification	CodeCode Available	1
When Contrastive Learning Meets Active Learning: A Novel Graph Active Learning Paradigm with Self-Supervision	Oct 30, 2020	Active LearningContrastive Learning	—Unverified	0
Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video Representation Leaning	Oct 29, 2020	Contrastive LearningData Augmentation	CodeCode Available	1
Cycle-Contrast for Self-Supervised Video Representation Learning	Oct 28, 2020	Action RecognitionContrastive Learning	—Unverified	0
Graph Contrastive Learning with Adaptive Augmentation	Oct 27, 2020	AttributeContrastive Learning	CodeCode Available	1
Contrastive Learning for Sequential Recommendation	Oct 27, 2020	Contrastive LearningData Augmentation	CodeCode Available	1
Robust Pre-Training by Adversarial Contrastive Learning	Oct 26, 2020	Adversarial RobustnessContrastive Learning	CodeCode Available	1
Contrastive Unsupervised Learning for Audio Fingerprinting	Oct 26, 2020	Contrastive Learning	—Unverified	0
CLRGaze: Contrastive Learning of Representations for Eye Movement Signals	Oct 25, 2020	BIG-bench Machine LearningContrastive Learning	CodeCode Available	0
Iterative Graph Self-Distillation	Oct 23, 2020	Contrastive LearningGraph Learning	—Unverified	0
CLOUD: Contrastive Learning of Unsupervised Dynamics	Oct 23, 2020	Contrastive Learning	—Unverified	0
Multilingual BERT Post-Pretraining Alignment	Oct 23, 2020	Contrastive LearningLanguage Modeling	—Unverified	0
Momentum Contrast Speaker Representation Learning	Oct 22, 2020	Contrastive LearningMetric Learning	—Unverified	0
Graph Contrastive Learning with Augmentations	Oct 22, 2020	Contrastive LearningRepresentation Learning	CodeCode Available	1
Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction	Oct 22, 2020	Contrastive LearningPrediction	CodeCode Available	1
Contrastive Learning with Adversarial Examples	Oct 22, 2020	Contrastive LearningSelf-Supervised Learning	—Unverified	0
A Framework for Generative and Contrastive Learning of Audio Representations	Oct 22, 2020	Contrastive Learning	—Unverified	0
Neural Audio Fingerprint for High-specific Audio Retrieval based on Contrastive Learning	Oct 22, 2020	Audio FingerprintContrastive Learning	CodeCode Available	1
Contrastive Self-Supervised Learning for Wireless Power Control	Oct 22, 2020	Contrastive LearningSelf-Supervised Learning	CodeCode Available	0

Show:10 25 50

← PrevPage 258 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