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 1051–1075 of 6661 papers

Title	Date	Tasks	Status	Hype
Position-Aware Subgraph Neural Networks with Data-Efficient Learning	Nov 1, 2022	Contrastive LearningPosition	CodeCode Available	1
A picture of the space of typical learnable tasks	Oct 31, 2022	Contrastive LearningMeta-Learning	CodeCode Available	1
A simple, efficient and scalable contrastive masked autoencoder for learning visual representations	Oct 30, 2022	Contrastive LearningSelf-Supervised Learning	CodeCode Available	1
Speaker Representation Learning via Contrastive Loss with Maximal Speaker Separability	Oct 29, 2022	Contrastive LearningData Augmentation	CodeCode Available	1
Differentiable Data Augmentation for Contrastive Sentence Representation Learning	Oct 29, 2022	Contrastive LearningData Augmentation	CodeCode Available	1
DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest Recommendation	Oct 29, 2022	Contrastive LearningDisentanglement	CodeCode Available	1
cRedAnno+: Annotation Exploitation in Self-Explanatory Lung Nodule Diagnosis	Oct 28, 2022	Active LearningAttribute	CodeCode Available	1
Pretraining Respiratory Sound Representations using Metadata and Contrastive Learning	Oct 27, 2022	Audio ClassificationClassification	CodeCode Available	1
Robust Data2vec: Noise-robust Speech Representation Learning for ASR by Combining Regression and Improved Contrastive Learning	Oct 27, 2022	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	1
IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text	Oct 26, 2022	Activity RecognitionContrastive Learning	CodeCode Available	1
Broken Neural Scaling Laws	Oct 26, 2022	Adversarial RobustnessContinual Learning	CodeCode Available	1
Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations	Oct 26, 2022	Contrastive LearningSemantic Segmentation	CodeCode Available	1
MABEL: Attenuating Gender Bias using Textual Entailment Data	Oct 26, 2022	Contrastive LearningFairness	CodeCode Available	1
Unsupervised Anomaly Detection for Auditing Data and Impact of Categorical Encodings	Oct 25, 2022	Anomaly DetectionContrastive Learning	CodeCode Available	1
Contrastive Representation Learning for Gaze Estimation	Oct 24, 2022	Contrastive LearningData Augmentation	CodeCode Available	1
Rethinking Rotation in Self-Supervised Contrastive Learning: Adaptive Positive or Negative Data Augmentation	Oct 23, 2022	Contrastive LearningData Augmentation	CodeCode Available	1
Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings	Oct 23, 2022	Acoustic Unit DiscoveryContrastive Learning	CodeCode Available	1
Neural Eigenfunctions Are Structured Representation Learners	Oct 23, 2022	Contrastive LearningData Augmentation	CodeCode Available	1
Twin Contrastive Learning for Online Clustering	Oct 21, 2022	ClusteringContrastive Learning	CodeCode Available	1
Exploring Representation-Level Augmentation for Code Search	Oct 21, 2022	Code SearchContrastive Learning	CodeCode Available	1
Contrastive Prototypical Network with Wasserstein Confidence Penalty	Oct 21, 2022	Contrastive LearningFew-Shot Learning	CodeCode Available	1
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
Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checking	Oct 19, 2022	Chinese Spell CheckingContrastive Learning	CodeCode Available	1
DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph	Oct 19, 2022	Contrastive LearningDisentanglement	CodeCode Available	1

Show:10 25 50

← PrevPage 43 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