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 5326–5350 of 6661 papers

Title	Date	Tasks	Status	Hype
ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition	Feb 1, 2022	Activity RecognitionContrastive Learning	—Unverified	0
CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery	Feb 1, 2022	Contrastive LearningDiversity	CodeCode Available	1
HCSC: Hierarchical Contrastive Selective Coding	Feb 1, 2022	Contrastive LearningRepresentation Learning	CodeCode Available	1
Learning Robust Representation through Graph Adversarial Contrastive Learning	Jan 31, 2022	Contrastive LearningGraph Representation Learning	—Unverified	0
Learning to Hash Naturally Sorts	Jan 31, 2022	Contrastive LearningDeep Hashing	—Unverified	0
Contrastive Learning from Demonstrations	Jan 30, 2022	Contrastive Learningreinforcement-learning	—Unverified	0
Generalizing similarity in noisy setups: the DIBS phenomenon	Jan 30, 2022	Contrastive Learning	—Unverified	0
Self-Supervised Moving Vehicle Detection from Audio-Visual Cues	Jan 30, 2022	Contrastive Learningvehicle detection	—Unverified	0
Investigating Why Contrastive Learning Benefits Robustness Against Label Noise	Jan 29, 2022	Contrastive Learning	—Unverified	0
Understanding Deep Contrastive Learning via Coordinate-wise Optimization	Jan 29, 2022	Contrastive LearningRepresentation Learning	—Unverified	0
SupWMA: Consistent and Efficient Tractography Parcellation of Superficial White Matter with Deep Learning	Jan 29, 2022	Contrastive Learning	CodeCode Available	1
Hybrid Contrastive Learning with Cluster Ensemble for Unsupervised Person Re-identification	Jan 28, 2022	ClusteringClustering Ensemble	—Unverified	0
Syfer: Neural Obfuscation for Private Data Release	Jan 28, 2022	Contrastive Learning	—Unverified	0
PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings	Jan 28, 2022	Contrastive LearningOpen-Ended Question Answering	CodeCode Available	1
Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives	Jan 27, 2022	Contrastive LearningOut-of-Distribution Detection	CodeCode Available	1
Contrastive Embedding Distribution Refinement and Entropy-Aware Attention for 3D Point Cloud Classification	Jan 27, 2022	3D Point Cloud ClassificationContrastive Learning	CodeCode Available	0
CodeRetriever: Unimodal and Bimodal Contrastive Learning for Code Search	Jan 26, 2022	Code SearchContrastive Learning	—Unverified	0
Pair-Level Supervised Contrastive Learning for Natural Language Inference	Jan 26, 2022	Contrastive LearningNatural Language Inference	—Unverified	0
Visualizing the Diversity of Representations Learned by Bayesian Neural Networks	Jan 26, 2022	Contrastive LearningDecision Making	—Unverified	0
Modeling Multi-level Context for Informational Bias Detection by Contrastive Learning and Sentential Graph Network	Jan 25, 2022	ArticlesBias Detection	—Unverified	0
Cross-Domain Document Layout Analysis Using Document Style Guide	Jan 24, 2022	Contrastive LearningDocument Layout Analysis	—Unverified	0
Learning Graph Augmentations to Learn Graph Representations	Jan 24, 2022	Contrastive Learning	CodeCode Available	0
Gradient-guided Unsupervised Text Style Transfer via Contrastive Learning	Jan 23, 2022	Adversarial AttackContrastive Learning	—Unverified	0
OntoProtein: Protein Pretraining With Gene Ontology Embedding	Jan 23, 2022	Contrastive LearningKnowledge Graphs	CodeCode Available	1
PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning	Jan 22, 2022	Contrastive LearningPartial Label Learning	CodeCode Available	2

Show:10 25 50

← PrevPage 214 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