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 4926–4950 of 6661 papers

Title	Date	Tasks	Status	Hype
Improving Long Tailed Document-Level Relation Extraction via Easy Relation Augmentation and Contrastive Learning	May 21, 2022	Contrastive LearningDocument-level Relation Extraction	—Unverified	0
Robust Task-Oriented Dialogue Generation with Contrastive Pre-training and Adversarial Filtering	May 20, 2022	Contrastive LearningDialogue Generation	—Unverified	0
Data Augmentation for Compositional Data: Advancing Predictive Models of the Microbiome	May 20, 2022	Contrastive LearningData Augmentation	CodeCode Available	0
Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformer	May 20, 2022	Contrastive LearningRepresentation Learning	CodeCode Available	1
Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity Recognition	May 20, 2022	Activity RecognitionContrastive Learning	CodeCode Available	1
What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders	May 20, 2022	Contrastive LearningLink Prediction	CodeCode Available	6
Label-invariant Augmentation for Semi-Supervised Graph Classification	May 19, 2022	ClassificationContrastive Learning	—Unverified	0
A graph-transformer for whole slide image classification	May 19, 2022	ClassificationContrastive Learning	CodeCode Available	1
A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation Extraction	May 19, 2022	Contrastive LearningRelation	CodeCode Available	1
Personalized Prompt for Sequential Recommendation	May 19, 2022	Contrastive LearningSequential Recommendation	—Unverified	0
RankGen: Improving Text Generation with Large Ranking Models	May 19, 2022	Contrastive LearningLanguage Modeling	CodeCode Available	1
Free Lunch for Surgical Video Understanding by Distilling Self-Supervisions	May 19, 2022	Contrastive LearningSelf-Supervised Learning	CodeCode Available	1
Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning	May 19, 2022	Contrastive LearningImage Stylization	CodeCode Available	1
Masked Image Modeling with Denoising Contrast	May 19, 2022	Contrastive LearningDenoising	CodeCode Available	1
Improving Micro-video Recommendation via Contrastive Multiple Interests	May 19, 2022	Contrastive Learning	CodeCode Available	0
CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning	May 18, 2022	Contrastive LearningText Generation	—Unverified	0
Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision	May 18, 2022	Contrastive LearningRelation	CodeCode Available	0
Attention-aware contrastive learning for predicting T cell receptor-antigen binding specificity	May 17, 2022	Contrastive LearningSpecificity	—Unverified	0
Dynamic Recognition of Speakers for Consent Management by Contrastive Embedding Replay	May 17, 2022	Contrastive LearningInductive Bias	—Unverified	0
A two-steps approach to improve the performance of Android malware detectors	May 17, 2022	Android Malware DetectionBinary Classification	—Unverified	0
FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization	May 16, 2022	Abstractive Text SummarizationContrastive Learning	CodeCode Available	1
Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization	May 15, 2022	Contrastive LearningIntent Detection	CodeCode Available	1
Toward a Geometrical Understanding of Self-supervised Contrastive Learning	May 13, 2022	Contrastive LearningData Augmentation	—Unverified	0
Arithmetic-Based Pretraining -- Improving Numeracy of Pretrained Language Models	May 13, 2022	Contrastive LearningReading Comprehension	CodeCode Available	0
PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning	May 13, 2022	Bilevel OptimizationContrastive Learning	—Unverified	0

Show:10 25 50

← PrevPage 198 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