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 4426–4450 of 6661 papers

Title	Date	Tasks	Status	Hype
SAICL: Student Modelling with Interaction-level Auxiliary Contrastive Tasks for Knowledge Tracing and Dropout Prediction	Oct 7, 2022	Contrastive LearningData Augmentation	—Unverified	0
Zero-shot stance detection based on cross-domain feature enhancement by contrastive learning	Oct 7, 2022	Contrastive LearningStance Detection	—Unverified	0
Unsupervised Semantic Representation Learning of Scientific Literature Based on Graph Attention Mechanism and Maximum Mutual Information	Oct 7, 2022	Contrastive LearningGraph Attention	—Unverified	0
Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative	Oct 7, 2022	Contrastive LearningFairness	CodeCode Available	1
Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding	Oct 7, 2022	Contrastive LearningMedical Code Prediction	CodeCode Available	1
Unsupervised Domain Adaptation for COVID-19 Information Service with Contrastive Adversarial Domain Mixup	Oct 6, 2022	Contrastive LearningDomain Adaptation	—Unverified	0
Brief Introduction to Contrastive Learning Pretext Tasks for Visual Representation	Oct 6, 2022	Contrastive LearningSelf-Supervised Learning	—Unverified	0
Uncovering the Structural Fairness in Graph Contrastive Learning	Oct 6, 2022	Contrastive LearningFairness	CodeCode Available	1
Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding	Oct 6, 2022	3D Object ClassificationContrastive Learning	CodeCode Available	1
Content-Based Search for Deep Generative Models	Oct 6, 2022	Contrastive LearningImage and Sketch based Model Retrieval	CodeCode Available	2
CLAD: A Contrastive Learning based Approach for Background Debiasing	Oct 6, 2022	Contrastive Learningimage-classification	CodeCode Available	0
Making Your First Choice: To Address Cold Start Problem in Vision Active Learning	Oct 5, 2022	Active LearningContrastive Learning	CodeCode Available	1
Jitter Does Matter: Adapting Gaze Estimation to New Domains	Oct 5, 2022	Adversarial AttackContrastive Learning	—Unverified	0
Revisiting Graph Contrastive Learning from the Perspective of Graph Spectrum	Oct 5, 2022	Contrastive Learning	CodeCode Available	1
CFL-Net: Image Forgery Localization Using Contrastive Learning	Oct 4, 2022	Contrastive LearningImage Manipulation	CodeCode Available	0
When and why vision-language models behave like bags-of-words, and what to do about it?	Oct 4, 2022	Contrastive LearningRetrieval	CodeCode Available	2
Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions	Oct 4, 2022	Contrastive LearningGeneralization Bounds	—Unverified	0
Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimization	Oct 4, 2022	Contrastive LearningImage Retrieval	CodeCode Available	1
Self-supervised Pre-training for Semantic Segmentation in an Indoor Scene	Oct 4, 2022	Contrastive LearningObject Rearrangement	—Unverified	0
A Study on the Efficiency and Generalization of Light Hybrid Retrievers	Oct 4, 2022	Adversarial AttackContrastive Learning	—Unverified	0
CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning	Oct 4, 2022	Anomaly DetectionContrastive Learning	CodeCode Available	0
Backdoor Attacks in the Supply Chain of Masked Image Modeling	Oct 4, 2022	Contrastive LearningSelf-Supervised Learning	—Unverified	0
COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation	Oct 4, 2022	3D Semantic SegmentationContrastive Learning	CodeCode Available	1
ContraCLM: Contrastive Learning For Causal Language Model	Oct 3, 2022	Code GenerationCode Search	CodeCode Available	1
CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training	Oct 3, 2022	3D Point Cloud ClassificationContrastive Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 178 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