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 6176–6200 of 6661 papers

Title	Date	Tasks	Status	Hype
LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions	Apr 2, 2021	Contrastive LearningImage Generation	CodeCode Available	1
Detecting Anomalies Through Contrast in Heterogeneous Data	Apr 2, 2021	Anomaly DetectionContrastive Learning	—Unverified	0
ArSarcasm Shared Task: An Ensemble BERT Model for SarcasmDetection in Arabic Tweets	Apr 1, 2021	Contrastive LearningSarcasm Detection	—Unverified	0
Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processing	Apr 1, 2021	Contrastive LearningDenoising	CodeCode Available	0
Enriched Music Representations with Multiple Cross-modal Contrastive Learning	Apr 1, 2021	Contrastive LearningGenre classification	CodeCode Available	1
Jigsaw Clustering for Unsupervised Visual Representation Learning	Apr 1, 2021	ClusteringContrastive Learning	CodeCode Available	1
Unsupervised Sound Localization via Iterative Contrastive Learning	Apr 1, 2021	Contrastive Learning	—Unverified	0
Composable Augmentation Encoding for Video Representation Learning	Apr 1, 2021	Action RecognitionContrastive Learning	—Unverified	0
PointShuffleNet: Learning Non-Euclidean Features with Homotopy Equivalence and Mutual Information	Mar 31, 2021	Contrastive LearningPoint Cloud Classification	—Unverified	0
Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective	Mar 31, 2021	Contrastive LearningObject	CodeCode Available	1
Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation	Mar 31, 2021	Contrastive LearningDomain Adaptation	CodeCode Available	1
Denoise and Contrast for Category Agnostic Shape Completion	Mar 30, 2021	Contrastive LearningDenoising	CodeCode Available	1
Progressive Domain Expansion Network for Single Domain Generalization	Mar 30, 2021	Contrastive LearningDomain Generalization	CodeCode Available	1
Contrastive Learning of Single-Cell Phenotypic Representations for Treatment Classification	Mar 30, 2021	Action ClassificationClassification	—Unverified	0
Model-Contrastive Federated Learning	Mar 30, 2021	Contrastive LearningFederated Learning	CodeCode Available	1
CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning	Mar 30, 2021	Action LocalizationCoLA	CodeCode Available	1
ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification	Mar 30, 2021	Contrastive LearningPerson Re-Identification	CodeCode Available	1
Robust Audio-Visual Instance Discrimination	Mar 29, 2021	Action RecognitionContrastive Learning	—Unverified	0
Elsa: Energy-based learning for semi-supervised anomaly detection	Mar 29, 2021	Anomaly DetectionContrastive Learning	—Unverified	0
Classification of Seeds using Domain Randomization on Self-Supervised Learning Frameworks	Mar 29, 2021	Contrastive LearningGeneral Classification	—Unverified	0
Self-supervised Graph Neural Networks without explicit negative sampling	Mar 27, 2021	Contrastive LearningData Augmentation	CodeCode Available	1
Contrastive Domain Adaptation	Mar 26, 2021	Contrastive LearningDomain Adaptation	—Unverified	0
Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification	Mar 26, 2021	ClassificationContrastive Learning	—Unverified	0
Unsupervised Document Embedding via Contrastive Augmentation	Mar 26, 2021	Contrastive LearningData Augmentation	—Unverified	0
Rethinking Self-Supervised Learning: Small is Beautiful	Mar 25, 2021	Contrastive LearningSelf-Supervised Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 248 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