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 4341–4350 of 6661 papers

Title	Date	Tasks	Status	Hype
BioLORD: Learning Ontological Representations from Definitions (for Biomedical Concepts and their Textual Descriptions)	Oct 21, 2022	Contrastive Learningtext similarity	—Unverified	0
HCL: Improving Graph Representation with Hierarchical Contrastive Learning	Oct 21, 2022	Contrastive LearningGraph Classification	—Unverified	0
Visual-Semantic Contrastive Alignment for Few-Shot Image Classification	Oct 20, 2022	ClassificationContrastive Learning	—Unverified	0
Mathematical Justification of Hard Negative Mining via Isometric Approximation Theorem	Oct 20, 2022	Contrastive LearningMetric Learning	—Unverified	0
Apple of Sodom: Hidden Backdoors in Superior Sentence Embeddings via Contrastive Learning	Oct 20, 2022	Backdoor AttackContrastive Learning	—Unverified	0
Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models	Oct 20, 2022	Contrastive LearningNatural Language Inference	CodeCode Available	0
Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble	Oct 20, 2022	Contrastive Learningintent-classification	CodeCode Available	0
SSiT: Saliency-guided Self-supervised Image Transformer for Diabetic Retinopathy Grading	Oct 20, 2022	Contrastive LearningDiabetic Retinopathy Grading	CodeCode Available	1
Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?	Oct 20, 2022	Contrastive LearningRepresentation Learning	CodeCode Available	1
Controller-Guided Partial Label Consistency Regularization with Unlabeled Data	Oct 20, 2022	Contrastive LearningData Augmentation	—Unverified	0

Show:10 25 50

← PrevPage 435 of 667Next →

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