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 1476–1500 of 6661 papers

Title	Date	Tasks	Status	Hype
TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning	Nov 7, 2021	Contrastive LearningNatural Language Understanding	CodeCode Available	1
Hard Negative Sampling via Regularized Optimal Transport for Contrastive Representation Learning	Nov 4, 2021	Contrastive LearningRepresentation Learning	CodeCode Available	1
Callee: Recovering Call Graphs for Binaries with Transfer and Contrastive Learning	Nov 2, 2021	Contrastive LearningQuestion Answering	CodeCode Available	1
When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?	Nov 1, 2021	Adversarial RobustnessContrastive Learning	CodeCode Available	1
Towards the Generalization of Contrastive Self-Supervised Learning	Nov 1, 2021	Contrastive LearningData Augmentation	CodeCode Available	1
Improving Contrastive Learning on Imbalanced Seed Data via Open-World Sampling	Nov 1, 2021	AttributeContrastive Learning	CodeCode Available	1
Self-Supervised Learning Disentangled Group Representation as Feature	Oct 28, 2021	ColorizationContrastive Learning	CodeCode Available	1
Equivariant Contrastive Learning	Oct 28, 2021	Contrastive LearningSelf-Supervised Learning	CodeCode Available	1
FocusFace: Multi-task Contrastive Learning for Masked Face Recognition	Oct 28, 2021	Contrastive LearningFace Recognition	CodeCode Available	1
Robust Contrastive Learning Using Negative Samples with Diminished Semantics	Oct 27, 2021	Contrastive LearningData Augmentation	CodeCode Available	1
Image Quality Assessment using Contrastive Learning	Oct 25, 2021	Contrastive LearningImage Quality Assessment	CodeCode Available	1
Contrastive Learning for Neural Topic Model	Oct 25, 2021	Contrastive Learningmodel	CodeCode Available	1
Contrastive Neural Processes for Self-Supervised Learning	Oct 24, 2021	Contrastive LearningData Augmentation	CodeCode Available	1
Multi-view Contrastive Graph Clustering	Oct 22, 2021	ClusteringContrastive Learning	CodeCode Available	1
CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP	Oct 21, 2021	Contrastive LearningSelf-Supervised Learning	CodeCode Available	1
Text-Based Person Search with Limited Data	Oct 20, 2021	BenchmarkingContrastive Learning	CodeCode Available	1
Understanding Dimensional Collapse in Contrastive Self-supervised Learning	Oct 18, 2021	Contrastive LearningLearning Theory	CodeCode Available	1
Virtual Augmentation Supported Contrastive Learning of Sentence Representations	Oct 16, 2021	Contrastive LearningData Augmentation	CodeCode Available	1
Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problems	Oct 16, 2021	Contrastive LearningMath	CodeCode Available	1
Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation	Oct 15, 2021	3D Semantic SegmentationContrastive Learning	CodeCode Available	1
Decoupled Contrastive Learning	Oct 13, 2021	Contrastive LearningSelf-Supervised Learning	CodeCode Available	1
MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction	Oct 13, 2021	Contrastive LearningDocument Embedding	CodeCode Available	1
Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation	Oct 12, 2021	Contrastive LearningSequential Recommendation	CodeCode Available	1
Weakly Supervised Contrastive Learning	Oct 10, 2021	Contrastive LearningRepresentation Learning	CodeCode Available	1
Temperature as Uncertainty in Contrastive Learning	Oct 8, 2021	Contrastive LearningLinear evaluation	CodeCode Available	1

Show:10 25 50

← PrevPage 60 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