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 5776–5800 of 6661 papers

Title	Date	Tasks	Status	Hype
Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling	Sep 29, 2021	Contrastive LearningPhrase Grounding	—Unverified	0
Identity-Disentangled Adversarial Augmentation for Self-supervised Learning	Sep 29, 2021	Contrastive LearningData Augmentation	—Unverified	0
Contrastive Video-Language Segmentation	Sep 29, 2021	Contrastive LearningRelation	—Unverified	0
Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Id	Sep 29, 2021	ClusteringContrastive Learning	—Unverified	0
Towards Communication-Efficient and Privacy-Preserving Federated Representation Learning	Sep 29, 2021	Contrastive LearningFederated Learning	—Unverified	0
Boost-RS: Boosted Embeddings for Recommender Systems and its Application to Enzyme-Substrate Interaction Prediction	Sep 28, 2021	AttributeAuxiliary Learning	CodeCode Available	0
A Contrastive Learning Approach to Auroral Identification and Classification	Sep 28, 2021	ClassificationContrastive Learning	—Unverified	0
Modelling Neighbor Relation in Joint Space-Time Graph for Video Correspondence Learning	Sep 28, 2021	Contrastive LearningRelation	—Unverified	0
The JHU submission to VoxSRC-21: Track 3	Sep 28, 2021	ClusteringContrastive Learning	—Unverified	0
Dynamic Modeling of Hand-Object Interactions via Tactile Sensing.	Sep 27, 2021	Contrastive LearningImitation Learning	—Unverified	0
Click-through Rate Prediction with Auto-Quantized Contrastive Learning	Sep 27, 2021	Click-Through Rate PredictionContrastive Learning	—Unverified	0
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations	Sep 27, 2021	Contrastive LearningLanguage Modelling	CodeCode Available	1
Compressive Visual Representations	Sep 27, 2021	Contrastive LearningImage Classification	CodeCode Available	1
Self-Supervised Video Representation Learning by Video Incoherence Detection	Sep 26, 2021	Action RecognitionContrastive Learning	—Unverified	0
DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings	Sep 26, 2021	Contrastive LearningSemantic Textual Similarity	CodeCode Available	1
Cluster Analysis with Deep Embeddings and Contrastive Learning	Sep 26, 2021	ClusteringContrastive Learning	—Unverified	0
Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification	Sep 25, 2021	Contrastive LearningPerson Re-Identification	CodeCode Available	1
Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation	Sep 25, 2021	Contrastive LearningDescriptive	CodeCode Available	1
Contrastive Learning for Mitochondria Segmentation	Sep 25, 2021	Contrastive LearningSegmentation	—Unverified	0
Dense Contrastive Visual-Linguistic Pretraining	Sep 24, 2021	Contrastive LearningData Augmentation	—Unverified	0
GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction	Sep 24, 2021	Contrastive LearningData Augmentation	CodeCode Available	1
Self-supervised Learning for Semi-supervised Temporal Language Grounding	Sep 23, 2021	Contrastive LearningPseudo Label	—Unverified	0
Long Short View Feature Decomposition via Contrastive Video Representation Learning	Sep 23, 2021	Action RecognitionAction Segmentation	—Unverified	0
Learning Contrastive Representation for Semantic Correspondence	Sep 22, 2021	Contrastive LearningSemantic correspondence	—Unverified	0
Contrastive Learning for Fair Representations	Sep 22, 2021	AttributeContrastive Learning	—Unverified	0

Show:10 25 50

← PrevPage 232 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