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 5151–5175 of 6661 papers

Title	Date	Tasks	Status	Hype
Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation	Mar 26, 2022	Contrastive Learningimage-classification	CodeCode Available	1
Improving Contrastive Learning with Model Augmentation	Mar 25, 2022	Contrastive LearningData Augmentation	CodeCode Available	1
Multi-scale and Cross-scale Contrastive Learning for Semantic Segmentation	Mar 25, 2022	Contrastive LearningSemantic Segmentation	CodeCode Available	1
Unsupervised Pre-training for Temporal Action Localization Tasks	Mar 25, 2022	Action LocalizationContrastive Learning	CodeCode Available	1
Self-Supervised Predictive Learning: A Negative-Free Method for Sound Source Localization in Visual Scenes	Mar 25, 2022	Contrastive LearningSound Source Localization	CodeCode Available	1
Versatile Multi-Modal Pre-Training for Human-Centric Perception	Mar 25, 2022	Contrastive LearningHuman Parsing	CodeCode Available	1
Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation	Mar 25, 2022	Contrastive Learningimage-classification	CodeCode Available	2
Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap	Mar 25, 2022	ARCContrastive Learning	CodeCode Available	1
A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training	Mar 25, 2022	Contrastive Learning	—Unverified	0
Probing Representation Forgetting in Supervised and Unsupervised Continual Learning	Mar 24, 2022	Continual LearningContrastive Learning	—Unverified	0
On Understanding and Mitigating the Dimensional Collapse of Graph Contrastive Learning: a Non-Maximum Removal Approach	Mar 24, 2022	Contrastive LearningGraph Classification	—Unverified	0
Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation	Mar 24, 2022	Contrastive LearningGesture Generation	CodeCode Available	1
Tackling Online One-Class Incremental Learning by Removing Negative Contrasts	Mar 24, 2022	class-incremental learningClass Incremental Learning	—Unverified	0
Self-supervised Video-centralised Transformer for Video Face Clustering	Mar 24, 2022	ClusteringContrastive Learning	—Unverified	0
mcBERT: Momentum Contrastive Learning with BERT for Zero-Shot Slot Filling	Mar 24, 2022	Contrastive Learningslot-filling	—Unverified	0
Steganalysis of Image with Adaptively Parametric Activation	Mar 24, 2022	Contrastive LearningDiversity	—Unverified	0
Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation	Mar 23, 2022	Contrastive LearningImage-to-Image Translation	CodeCode Available	1
R3M: A Universal Visual Representation for Robot Manipulation	Mar 23, 2022	Contrastive LearningRobot Manipulation	CodeCode Available	2
Negative Selection by Clustering for Contrastive Learning in Human Activity Recognition	Mar 23, 2022	Activity RecognitionClustering	—Unverified	0
Text Transformations in Contrastive Self-Supervised Learning: A Review	Mar 22, 2022	Contrastive LearningRepresentation Learning	—Unverified	0
Towards Textual Out-of-Domain Detection without In-Domain Labels	Mar 22, 2022	Contrastive Learningintent-classification	—Unverified	0
Utterance Rewriting with Contrastive Learning in Multi-turn Dialogue	Mar 22, 2022	Contrastive LearningMulti-Task Learning	—Unverified	0
Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition	Mar 22, 2022	Contrastive LearningLong-tail Learning	—Unverified	0
CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation	Mar 22, 2022	Contrastive LearningRepresentation Learning	CodeCode Available	1
Unsupervised Deraining: Where Contrastive Learning Meets Self-similarity	Mar 22, 2022	Contrastive LearningImage Restoration	CodeCode Available	1

Show:10 25 50

← PrevPage 207 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