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 6651–6661 of 6661 papers

Title	Date	Tasks	Status
Dictionary Learning by Dynamical Neural Networks	May 23, 2018	Contrastive LearningDictionary Learning	—Unverified
Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning	May 22, 2018	Contrastive LearningRepresentation Learning	CodeCode Available
Adversarial Contrastive Estimation	May 9, 2018	Contrastive LearningKnowledge Graph Embeddings	—Unverified
Contrastive Learning of Emoji-based Representations for Resource-Poor Languages	Apr 3, 2018	Contrastive Learning	—Unverified
Sentiment Analysis of Code-Mixed Languages leveraging Resource Rich Languages	Apr 3, 2018	ClusteringContrastive Learning	CodeCode Available
Geometry-Contrastive GAN for Facial Expression Transfer	Feb 6, 2018	Contrastive LearningGenerative Adversarial Network	CodeCode Available
Contrastive Learning for Image Captioning	Oct 6, 2017	Contrastive LearningImage Captioning	—Unverified
Visual Transformation Aided Contrastive Learning for Video-Based Kinship Verification	Oct 1, 2017	Contrastive LearningDecoder	—Unverified
Time-Contrastive Learning Based DNN Bottleneck Features for Text-Dependent Speaker Verification	Apr 6, 2017	Contrastive LearningSpeaker Verification	—Unverified
Learning Text Similarity with Siamese Recurrent Networks	Aug 1, 2016	Contrastive LearningRepresentation Learning	CodeCode Available
Contrastive Learning Using Spectral Methods	Dec 1, 2013	ArticlesContrastive Learning	—Unverified

Show:10 25 50

← PrevPage 134 of 134Next →

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