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 2576–2600 of 6661 papers

Title	Date	Tasks	Status	Score
Contrastive Instruction-Trajectory Learning for Vision-Language Navigation	Dec 8, 2021	Contrastive LearningNavigate	CodeCode Available	5
Feature-Level Debiased Natural Language Understanding	Dec 11, 2022	Contrastive LearningNatural Language Understanding	CodeCode Available	5
Self-supervised Feature-Gate Coupling for Dynamic Network Pruning	Nov 29, 2021	Contrastive LearningNetwork Pruning	CodeCode Available	5
Learning Graph Augmentations to Learn Graph Representations	Jan 24, 2022	Contrastive Learning	CodeCode Available	5
Contrastive Instance Association for 4D Panoptic Segmentation using Sequences of 3D LiDAR Scans	Dec 1, 2021	4D Panoptic SegmentationAutonomous Navigation	CodeCode Available	5
Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment	Oct 21, 2023	Contrastive LearningDomain Adaptation	CodeCode Available	5
FBA-Net: Foreground and Background Aware Contrastive Learning for Semi-Supervised Atrium Segmentation	Jun 27, 2023	Contrastive LearningImage Segmentation	CodeCode Available	5
Learning Discriminative Visual-Text Representation for Polyp Re-Identification	Jul 20, 2023	ClusteringContrastive Learning	CodeCode Available	5
Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processing	Apr 1, 2021	Contrastive LearningDenoising	CodeCode Available	5
AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking	Oct 15, 2023	Contrastive LearningData Augmentation	CodeCode Available	5
Learning Contrastive Feature Representations for Facial Action Unit Detection	Feb 9, 2024	Action Unit DetectionBinary Classification	CodeCode Available	5
Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellings	May 4, 2022	Contrastive LearningData Augmentation	CodeCode Available	5
Latent Processes Identification From Multi-View Time Series	May 14, 2023	Contrastive LearningTime Series	CodeCode Available	5
Modeling User Intent Beyond Trigger: Incorporating Uncertainty for Trigger-Induced Recommendation	Aug 6, 2024	Contrastive Learning	CodeCode Available	5
FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning	Dec 1, 2022	Contrastive LearningRepresentation Learning	CodeCode Available	5
Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning	Jun 16, 2022	BenchmarkingClustering	CodeCode Available	5
Learn from Relation Information: Towards Prototype Representation Rectification for Few-Shot Relation Extraction	Jul 1, 2022	Contrastive LearningDomain Adaptation	CodeCode Available	5
Leave No One Behind: Online Self-Supervised Self-Distillation for Sequential Recommendation	Mar 22, 2024	ClusteringContrastive Learning	CodeCode Available	5
Fairness-aware Multi-view Clustering	Feb 11, 2023	ClusteringContrastive Learning	CodeCode Available	5
ContrastiveGaussian: High-Fidelity 3D Generation with Contrastive Learning and Gaussian Splatting	Apr 10, 2025	3D GenerationContrastive Learning	CodeCode Available	5
Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features	Jun 26, 2025	Contrastive LearningSelf-Supervised Learning	CodeCode Available	5
FairDgcl: Fairness-aware Recommendation with Dynamic Graph Contrastive Learning	Oct 23, 2024	Contrastive LearningData Augmentation	CodeCode Available	5
FPPL: An Efficient and Non-IID Robust Federated Continual Learning Framework	Nov 4, 2024	Continual LearningContrastive Learning	CodeCode Available	5
Large Language Models Meet Contrastive Learning: Zero-Shot Emotion Recognition Across Languages	Mar 25, 2025	Contrastive LearningDiversity	CodeCode Available	5
Large-Scale Hyperspectral Image Clustering Using Contrastive Learning	Nov 15, 2021	ClusteringContrastive Learning	CodeCode Available	5

Show:10 25 50

← PrevPage 104 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