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 1751–1775 of 6661 papers

Title	Date	Tasks	Status	Hype
Sequence-to-Sequence Contrastive Learning for Text Recognition	Dec 20, 2020	Contrastive LearningDecoder	CodeCode Available	1
Camera-aware Proxies for Unsupervised Person Re-Identification	Dec 19, 2020	ClusteringContrastive Learning	CodeCode Available	1
Joint Generative and Contrastive Learning for Unsupervised Person Re-identification	Dec 16, 2020	Contrastive LearningData Augmentation	CodeCode Available	1
ISD: Self-Supervised Learning by Iterative Similarity Distillation	Dec 16, 2020	Contrastive LearningSelf-Supervised Learning	CodeCode Available	1
CODE: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert Linking	Dec 14, 2020	Active LearningContrastive Learning	CodeCode Available	1
Contrastive Learning with Adversarial Perturbations for Conditional Text Generation	Dec 14, 2020	Conditional Text GenerationContrastive Learning	CodeCode Available	1
Self-supervised Text-independent Speaker Verification using Prototypical Momentum Contrastive Learning	Dec 13, 2020	ClusteringContrastive Learning	CodeCode Available	1
Contrastive Learning of Relative Position Regression for One-Shot Object Localization in 3D Medical Images	Dec 13, 2020	Contrastive LearningObject Localization	CodeCode Available	1
Multi-Objective Interpolation Training for Robustness to Label Noise	Dec 8, 2020	Contrastive LearningImage Classification	CodeCode Available	1
Fine-grained Angular Contrastive Learning with Coarse Labels	Dec 7, 2020	Contrastive LearningFew-Shot Learning	CodeCode Available	1
Cross-Domain Sentiment Classification with In-Domain Contrastive Learning	Dec 5, 2020	ClassificationContrastive Learning	CodeCode Available	1
SAM: Self-supervised Learning of Pixel-wise Anatomical Embeddings in Radiological Images	Dec 4, 2020	AnatomyComputed Tomography (CT)	CodeCode Available	1
Soft Contrastive Learning for Visual Localization	Dec 1, 2020	Contrastive LearningImage Retrieval	CodeCode Available	1
Pre-Trained Image Processing Transformer	Dec 1, 2020	Color Image DenoisingContrastive Learning	CodeCode Available	1
Multi-level Knowledge Distillation via Knowledge Alignment and Correlation	Dec 1, 2020	Contrastive LearningKnowledge Distillation	CodeCode Available	1
Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding	Nov 28, 2020	Anomaly DetectionChange Point Detection	CodeCode Available	1
Self supervised contrastive learning for digital histopathology	Nov 27, 2020	Contrastive LearningMedical Image Analysis	CodeCode Available	1
USCL: Pretraining Deep Ultrasound Image Diagnosis Model through Video Contrastive Representation Learning	Nov 25, 2020	Contrastive LearningMedical Image Analysis	CodeCode Available	1
CoMatch: Semi-supervised Learning with Contrastive Graph Regularization	Nov 23, 2020	Contrastive LearningRepresentation Learning	CodeCode Available	1
Exploring Contrastive Learning in Human Activity Recognition for Healthcare	Nov 23, 2020	Activity RecognitionContrastive Learning	CodeCode Available	1
Boosting Contrastive Self-Supervised Learning with False Negative Cancellation	Nov 23, 2020	Contrastive LearningRepresentation Learning	CodeCode Available	1
Geography-Aware Self-Supervised Learning	Nov 19, 2020	Contrastive Learningimage-classification	CodeCode Available	1
Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning	Nov 19, 2020	Contrastive Learningobject-detection	CodeCode Available	1
Dense Contrastive Learning for Self-Supervised Visual Pre-Training	Nov 18, 2020	Contrastive Learningimage-classification	CodeCode Available	1
Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning	Nov 17, 2020	ClassificationContrastive Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 71 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