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 6226–6250 of 6661 papers

Title	Date	Tasks	Status	Hype
FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders	Mar 11, 2021	Contrastive LearningFairness	—Unverified	0
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training	Mar 11, 2021	Contrastive LearningGPU	CodeCode Available	1
Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning	Mar 10, 2021	Contrastive LearningMeta Reinforcement Learning	—Unverified	0
Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations	Mar 10, 2021	Continual LearningContinual Semantic Segmentation	—Unverified	0
An Image-based Approach of Task-driven Driving Scene Categorization	Mar 10, 2021	AttributeAutonomous Vehicles	—Unverified	0
VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples	Mar 10, 2021	Action RecognitionContrastive Learning	CodeCode Available	1
FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding	Mar 10, 2021	Contrastive LearningCross-Domain Few-Shot Object Detection	CodeCode Available	1
Spatially Consistent Representation Learning	Mar 10, 2021	Contrastive Learningimage-classification	CodeCode Available	1
Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss	Mar 10, 2021	Autonomous DrivingContrastive Learning	—Unverified	0
Doubly Contrastive Deep Clustering	Mar 9, 2021	ClusteringContrastive Learning	CodeCode Available	1
SimTriplet: Simple Triplet Representation Learning with a Single GPU	Mar 9, 2021	Contrastive LearningGPU	CodeCode Available	1
Self-supervised SAR-optical Data Fusion and Land-cover Mapping using Sentinel-1/-2 Images	Mar 9, 2021	Contrastive LearningSelf-Supervised Learning	—Unverified	0
Bootstrapped Representation Learning on Graphs	Mar 8, 2021	Contrastive LearningLinear evaluation	—Unverified	0
CoDeGAN: Contrastive Disentanglement for Generative Adversarial Network	Mar 5, 2021	Contrastive LearningDisentanglement	CodeCode Available	0
Self-supervised Mean Teacher for Semi-supervised Chest X-ray Classification	Mar 5, 2021	Contrastive LearningGeneral Classification	CodeCode Available	0
Self-Supervised Longitudinal Neighbourhood Embedding	Mar 5, 2021	Contrastive LearningRepresentation Learning	CodeCode Available	1
Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Images	Mar 5, 2021	Anomaly DetectionContrastive Learning	CodeCode Available	1
Fine-Grained Off-Road Semantic Segmentation and Mapping via Contrastive Learning	Mar 5, 2021	Binary ClassificationContrastive Learning	—Unverified	0
Extending Contrastive Learning to Unsupervised Coreset Selection	Mar 5, 2021	Contrastive Learning	—Unverified	0
Contrastive Learning Meets Transfer Learning: A Case Study In Medical Image Analysis	Mar 4, 2021	Contrastive LearningMedical Image Analysis	—Unverified	0
SSTN: Self-Supervised Domain Adaptation Thermal Object Detection for Autonomous Driving	Mar 4, 2021	Autonomous DrivingAutonomous Vehicles	—Unverified	0
Contrastive learning of strong-mixing continuous-time stochastic processes	Mar 3, 2021	Contrastive LearningTime Series	—Unverified	0
Deep Clustering by Semantic Contrastive Learning	Mar 3, 2021	ClusteringContrastive Learning	—Unverified	0
Task-Adaptive Neural Network Search with Meta-Contrastive Learning	Mar 2, 2021	AutoMLContrastive Learning	CodeCode Available	1
SoundCLR: Contrastive Learning of Representations For Improved Environmental Sound Classification	Mar 2, 2021	Contrastive LearningData Augmentation	CodeCode Available	1

Show:10 25 50

← PrevPage 250 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