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 6476–6500 of 6661 papers

Title	Date	Tasks	Status	Hype
Unsupervised Representation Learning by InvariancePropagation	Oct 7, 2020	Contrastive LearningRepresentation Learning	CodeCode Available	1
Representation Learning for Sequence Data with Deep Autoencoding Predictive Components	Oct 7, 2020	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	1
Support-set bottlenecks for video-text representation learning	Oct 6, 2020	Contrastive LearningRepresentation Learning	—Unverified	0
A Contrastive Learning Approach for Training Variational Autoencoder Priors	Oct 6, 2020	Contrastive LearningImage Generation	—Unverified	0
CO2: Consistent Contrast for Unsupervised Visual Representation Learning	Oct 5, 2020	Contrastive Learningimage-classification	—Unverified	0
A Simple Framework for Uncertainty in Contrastive Learning	Oct 5, 2020	Contrastive LearningRepresentation Learning	—Unverified	0
EqCo: Equivalent Rules for Self-supervised Contrastive Learning	Oct 5, 2020	Contrastive LearningLinear evaluation	CodeCode Available	0
Unsupervised Reference-Free Summary Quality Evaluation via Contrastive Learning	Oct 5, 2020	Contrastive LearningDocument Summarization	CodeCode Available	1
Conditional Negative Sampling for Contrastive Learning of Visual Representations	Oct 5, 2020	Contrastive LearningInstance Segmentation	CodeCode Available	0
Contrastive Learning of Medical Visual Representations from Paired Images and Text	Oct 2, 2020	Contrastive LearningDescriptive	CodeCode Available	1
Hard Negative Mixing for Contrastive Learning	Oct 2, 2020	Contrastive LearningData Augmentation	CodeCode Available	1
Joint Contrastive Learning with Infinite Possibilities	Sep 30, 2020	Contrastive Learning	CodeCode Available	1
Driver Anomaly Detection: A Dataset and Contrastive Learning Approach	Sep 30, 2020	Anomaly DetectionContrastive Learning	CodeCode Available	1
Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning	Sep 29, 2020	Contrastive LearningMeta Reinforcement Learning	CodeCode Available	0
CoKe: Localized Contrastive Learning for Robust Keypoint Detection	Sep 29, 2020	Contrastive LearningKeypoint Detection	—Unverified	0
Function Contrastive Learning of Transferable Representations	Sep 28, 2020	Contrastive LearningFew-Shot Learning	—Unverified	0
What About Taking Policy as Input of Value Function: Policy-extended Value Function Approximator	Sep 28, 2020	continuous-controlContinuous Control	—Unverified	0
DROPS: Deep Retrieval of Physiological Signals via Attribute-specific Clinical Prototypes	Sep 28, 2020	AttributeClustering	—Unverified	0
G-SimCLR: Self-Supervised Contrastive Learning with Guided Projection via Pseudo Labelling	Sep 28, 2020	Contrastive LearningDenoising	CodeCode Available	1
In-sample Contrastive Learning and Consistent Attention for Weakly Supervised Object Localization	Sep 25, 2020	Contrastive LearningObject	CodeCode Available	0
G-SimCLR : Self-Supervised Contrastive Learning with Guided Projection via Pseudo Labelling	Sep 25, 2020	Contrastive LearningDenoising	CodeCode Available	1
Structure Aware Negative Sampling in Knowledge Graphs	Sep 23, 2020	Contrastive LearningKnowledge Graphs	—Unverified	0
Label-Efficient Multi-Task Segmentation using Contrastive Learning	Sep 23, 2020	Contrastive LearningMulti-Task Learning	CodeCode Available	1
Feature Distillation With Guided Adversarial Contrastive Learning	Sep 21, 2020	Adversarial RobustnessContrastive Learning	—Unverified	0
Contrastive Clustering	Sep 21, 2020	ClusteringContrastive Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 260 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