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 1301–1325 of 6661 papers

Title	Date	Tasks	Status	Hype
Learning to Revise References for Faithful Summarization	Apr 13, 2022	AttributeClinical Knowledge	CodeCode Available	1
CLMLF:A Contrastive Learning and Multi-Layer Fusion Method for Multimodal Sentiment Detection	Apr 12, 2022	Contrastive LearningSentiment Analysis	CodeCode Available	1
GMSS: Graph-Based Multi-Task Self-Supervised Learning for EEG Emotion Recognition	Apr 12, 2022	Contrastive LearningEEG	CodeCode Available	1
A Comparative Study of Pre-trained Encoders for Low-Resource Named Entity Recognition	Apr 11, 2022	Contrastive LearningLow Resource Named Entity Recognition	CodeCode Available	1
Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning	Apr 11, 2022	Contrastive LearningGraph Generation	CodeCode Available	1
BankNote-Net: Open dataset for assistive universal currency recognition	Apr 7, 2022	Contrastive LearningFew-Shot Learning	CodeCode Available	1
Audio-Visual Person-of-Interest DeepFake Detection	Apr 6, 2022	Contrastive LearningDeepFake Detection	CodeCode Available	1
RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection	Apr 6, 2022	Contrastive LearningOut-of-Distribution Detection	CodeCode Available	1
PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations	Apr 6, 2022	Contrastive LearningDecision Making	CodeCode Available	1
Semi-supervised Semantic Segmentation with Error Localization Network	Apr 5, 2022	Contrastive LearningSegmentation	CodeCode Available	1
Lip to Speech Synthesis with Visual Context Attentional GAN	Apr 4, 2022	Contrastive LearningGenerative Adversarial Network	CodeCode Available	1
POS-BERT: Point Cloud One-Stage BERT Pre-Training	Apr 3, 2022	Contrastive LearningLanguage Modeling	CodeCode Available	1
Graph Enhanced Contrastive Learning for Radiology Findings Summarization	Apr 1, 2022	Contrastive Learning	CodeCode Available	1
Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings	Apr 1, 2022	Contrastive LearningKnowledge Distillation	CodeCode Available	1
Automatic Biomedical Term Clustering by Learning Fine-grained Term Representations	Apr 1, 2022	ClusteringContrastive Learning	CodeCode Available	1
Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization	Mar 31, 2022	Action LocalizationClassification	CodeCode Available	1
Video-Text Representation Learning via Differentiable Weak Temporal Alignment	Mar 31, 2022	Contrastive LearningDynamic Time Warping	CodeCode Available	1
Fair Contrastive Learning for Facial Attribute Classification	Mar 30, 2022	AttributeClassification	CodeCode Available	1
Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo	Mar 30, 2022	Contrastive Learning	CodeCode Available	1
In-N-Out Generative Learning for Dense Unsupervised Video Segmentation	Mar 29, 2022	Contrastive LearningSemantic Segmentation	CodeCode Available	1
SIOD: Single Instance Annotated Per Category Per Image for Object Detection	Mar 29, 2022	Contrastive LearningObject	CodeCode Available	1
Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentation	Mar 29, 2022	Contrastive LearningRelation	CodeCode Available	1
Large-scale Bilingual Language-Image Contrastive Learning	Mar 28, 2022	Contrastive LearningProper Noun	CodeCode Available	1
UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning	Mar 28, 2022	Contrastive LearningLearning with noisy labels	CodeCode Available	1
Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning	Mar 28, 2022	Action ClassificationContrastive Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 53 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