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 6626–6650 of 6661 papers

Title	Date	Tasks	Status	Hype
Align, Attend and Locate: Chest X-Ray Diagnosis via Contrast Induced Attention Network With Limited Supervision	Oct 1, 2019	Contrastive Learning	—Unverified	0
Annotated Guidelines and Building Reference Corpus for Myanmar-English Word Alignment	Sep 25, 2019	Contrastive LearningWord Alignment	—Unverified	0
Large Scale Adversarial Representation Learning	Jul 4, 2019	Contrastive LearningImage Generation	CodeCode Available	1
Reducing Word Omission Errors in Neural Machine Translation: A Contrastive Learning Approach	Jul 1, 2019	Contrastive LearningMachine Translation	—Unverified	0
Contrastive Multiview Coding	Jun 13, 2019	Contrastive LearningSelf-Supervised Action Recognition	CodeCode Available	1
Online Object Representations with Contrastive Learning	Jun 10, 2019	Contrastive LearningObject	—Unverified	0
Unified Visual-Semantic Embeddings: Bridging Vision and Language With Structured Meaning Representations	Jun 1, 2019	Contrastive LearningCross-Modal Retrieval	CodeCode Available	0
Hebbian-Descent	May 25, 2019	Contrastive Learning	—Unverified	0
Data-Efficient Image Recognition with Contrastive Predictive Coding	May 22, 2019	Contrastive LearningGeneral Classification	CodeCode Available	0
Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification	May 11, 2019	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified	0
Supporting Analysis of Dimensionality Reduction Results with Contrastive Learning	May 10, 2019	ClusteringContrastive Learning	—Unverified	0
Adversarial Defense Framework for Graph Neural Network	May 9, 2019	Adversarial DefenseContrastive Learning	—Unverified	0
Contrastive Learning for Lifted Networks	May 7, 2019	Contrastive Learning	—Unverified	0
Sparse Dictionary Learning by Dynamical Neural Networks	May 1, 2019	Contrastive LearningDictionary Learning	—Unverified	0
UniVSE: Robust Visual Semantic Embeddings via Structured Semantic Representations	Apr 11, 2019	Contrastive LearningCross-Modal Retrieval	CodeCode Available	1
Local Aggregation for Unsupervised Learning of Visual Embeddings	Mar 29, 2019	ClusteringContrastive Learning	CodeCode Available	0
Statistically-informed deep learning for gravitational wave parameter estimation	Mar 5, 2019	Contrastive LearningDeep Learning	—Unverified	0
A Theoretical Analysis of Contrastive Unsupervised Representation Learning	Feb 25, 2019	Contrastive LearningGeneral Classification	—Unverified	0
Contrastive Variational Autoencoder Enhances Salient Features	Feb 12, 2019	Contrastive Learning	CodeCode Available	0
Contrastive Learning from Pairwise Measurements	Dec 1, 2018	Contrastive LearningData Augmentation	—Unverified	0
DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization	Nov 6, 2018	Contrastive LearningDocument Summarization	CodeCode Available	0
Contrastive Video Representation Learning via Adversarial Perturbations	Jul 24, 2018	Action RecognitionBinary Classification	—Unverified	0
Mask-Guided Contrastive Attention Model for Person Re-Identification	Jun 1, 2018	Contrastive LearningPerson Re-Identification	CodeCode Available	0
Dictionary Learning by Dynamical Neural Networks	May 23, 2018	Contrastive LearningDictionary Learning	—Unverified	0
Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning	May 22, 2018	Contrastive LearningRepresentation Learning	CodeCode Available	0

Show:10 25 50

← PrevPage 266 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