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 1526–1550 of 6661 papers

Title	Date	Tasks	Status	Hype
Semi-supervised Contrastive Learning for Label-efficient Medical Image Segmentation	Sep 15, 2021	Contrastive LearningImage Segmentation	CodeCode Available	1
CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning	Sep 15, 2021	Contrastive LearningFew-shot NER	CodeCode Available	1
SupCL-Seq: Supervised Contrastive Learning for Downstream Optimized Sequence Representations	Sep 15, 2021	CoLAContrastive Learning	CodeCode Available	1
Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning	Sep 13, 2021	Contrastive LearningIntent Detection	CodeCode Available	1
Pairwise Supervised Contrastive Learning of Sentence Representations	Sep 12, 2021	Contrastive LearningNatural Language Inference	CodeCode Available	1
Exploring Task Difficulty for Few-Shot Relation Extraction	Sep 12, 2021	Contrastive LearningMeta-Learning	CodeCode Available	1
Contrastive Quantization with Code Memory for Unsupervised Image Retrieval	Sep 11, 2021	Contrastive LearningDeep Hashing	CodeCode Available	1
Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization	Sep 10, 2021	Abstractive Dialogue SummarizationArticles	CodeCode Available	1
Efficient Contrastive Learning via Novel Data Augmentation and Curriculum Learning	Sep 10, 2021	Continual PretrainingContrastive Learning	CodeCode Available	1
TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation	Sep 10, 2021	Contrastive LearningDomain Adaptation	CodeCode Available	1
ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding	Sep 9, 2021	Contrastive LearningData Augmentation	CodeCode Available	1
Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse Contexts	Sep 9, 2021	Contrastive LearningRepresentation Learning	CodeCode Available	1
Smoothed Contrastive Learning for Unsupervised Sentence Embedding	Sep 9, 2021	Contrastive LearningSentence	CodeCode Available	1
Sequence Level Contrastive Learning for Text Summarization	Sep 8, 2021	Abstractive Text SummarizationContrastive Learning	CodeCode Available	1
Supervised Contrastive Learning for Multimodal Unreliable News Detection in COVID-19 Pandemic	Sep 4, 2021	ArticlesContrastive Learning	CodeCode Available	1
Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation	Sep 3, 2021	Contrastive LearningDecoder	CodeCode Available	1
Self-supervised Pseudo Multi-class Pre-training for Unsupervised Anomaly Detection and Segmentation in Medical Images	Sep 3, 2021	Anomaly DetectionContrastive Learning	CodeCode Available	1
Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning	Sep 2, 2021	Contrastive LearningLanguage Modeling	CodeCode Available	1
Memory Augmented Multi-Instance Contrastive Predictive Coding for Sequential Recommendation	Sep 1, 2021	Contrastive LearningSequential Recommendation	CodeCode Available	1
ReMeDi: Resources for Multi-domain, Multi-service, Medical Dialogues	Sep 1, 2021	BenchmarkingContrastive Learning	CodeCode Available	1
Multi-Sample based Contrastive Loss for Top-k Recommendation	Sep 1, 2021	Contrastive LearningData Augmentation	CodeCode Available	1
ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasets	Aug 31, 2021	ClassificationContrastive Learning	CodeCode Available	1
When Do Contrastive Learning Signals Help Spatio-Temporal Graph Forecasting?	Aug 26, 2021	Contrastive LearningData Augmentation	CodeCode Available	1
Enhanced Seq2Seq Autoencoder via Contrastive Learning for Abstractive Text Summarization	Aug 26, 2021	Abstractive Text SummarizationContrastive Learning	CodeCode Available	1
Alleviating Exposure Bias via Contrastive Learning for Abstractive Text Summarization	Aug 26, 2021	Abstractive Text SummarizationContrastive Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 62 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