SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2701–2750 of 6661 papers

TitleStatusHype
Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic RepresentationsCode1
Unifying Structure and Language Semantic for Efficient Contrastive Knowledge Graph Completion with Structured Entity Anchors—0
Large Language Model based Long-tail Query Rewriting in Taobao SearchCode3
Multi-View Causal Representation Learning with Partial ObservabilityCode1
Can CLIP Help Sound Source Localization?Code1
Temporal Graph Representation Learning with Adaptive Augmentation Contrastive—0
Topology Only Pre-Training: Towards Generalised Multi-Domain Graph ModelsCode0
SCONE-GAN: Semantic Contrastive learning-based Generative Adversarial Network for an end-to-end image translation—0
Contrastive Multi-Level Graph Neural Networks for Session-based Recommendation—0
An Efficient Self-Supervised Cross-View Training For Sentence EmbeddingCode1
Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive LearningCode0
CycleCL: Self-supervised Learning for Periodic Videos—0
Contrastive Multi-Modal Representation Learning for Spark Plug Fault Diagnosis—0
Contrastive Deep Nonnegative Matrix Factorization for Community DetectionCode1
FaMeSumm: Investigating and Improving Faithfulness of Medical SummarizationCode1
CheX-Nomaly: Segmenting Lung Abnormalities from Chest Radiographs using Machine Learning—0
Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-trainingCode1
SMORE: Score Models for Offline Goal-Conditioned Reinforcement Learning—0
AI for Interpretable Chemistry: Predicting Radical Mechanistic Pathways via Contrastive Learning—0
Contrastive Modules with Temporal Attention for Multi-Task Reinforcement LearningCode0
FLAP: Fast Language-Audio Pre-training—0
Cross-Modal Information-Guided Network using Contrastive Learning for Point Cloud RegistrationCode1
Multi-level Relation Learning for Cross-domain Few-shot Hyperspectral Image ClassificationCode0
VIGraph: Generative Self-supervised Learning for Class-Imbalanced Node Classification—0
Learning Intra and Inter-Camera Invariance for Isolated Camera Supervised Person Re-identificationCode0
DyTSCL: Dynamic graph representation via tempo-structural contrastive learningCode0
CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked AutoencodersCode1
Rethinking Samples Selection for Contrastive Learning: Mining of Potential Samples—0
REBAR: Retrieval-Based Reconstruction for Time-series Contrastive LearningCode1
On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval—0
TPSeNCE: Towards Artifact-Free Realistic Rain Generation for Deraining and Object Detection in RainCode1
BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable BasisCode1
Medi-CAT: Contrastive Adversarial Training for Medical Image Classification—0
SimMMDG: A Simple and Effective Framework for Multi-modal Domain GeneralizationCode1
FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent SpaceCode1
Uncertainty-guided Boundary Learning for Imbalanced Social Event DetectionCode0
Improving Medical Visual Representations via Radiology Report Generation—0
FLIP: Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR PredictionCode1
Adversarial Bootstrapped Question Representation Learning for Knowledge TracingCode0
Adversarial Examples Are Not Real FeaturesCode1
Simple and Asymmetric Graph Contrastive Learning without AugmentationsCode1
Retrofitting Light-weight Language Models for Emotions using Supervised Contrastive Learning—0
CHAIN: Exploring Global-Local Spatio-Temporal Information for Improved Self-Supervised Video Hashing—0
Towards Generalized Multi-stage Clustering: Multi-view Self-distillation—0
BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and MappingCode1
A Unique Training Strategy to Enhance Language Models Capabilities for Health Mention Detection from Social Media Content—0
Empowering Collaborative Filtering with Principled Adversarial Contrastive LossCode1
Leveraging Multimodal Features and Item-level User Feedback for Bundle ConstructionCode1
ReConTab: Regularized Contrastive Representation Learning for Tabular Data—0
Alignment and Outer Shell Isotropy for Hyperbolic Graph Contrastive Learning—0
Show:102550
← PrevPage 55 of 134Next →
All datasetsimagenet-1k10,000 People - Human Pose Recognition DataCIFAR-10STL-10

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6—Unverified
2ResNet50ImageNet Top-1 Accuracy73—Unverified
3ResNet50ImageNet Top-1 Accuracy71.1—Unverified
4ResNet50ImageNet Top-1 Accuracy69.3—Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6—Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8—Unverified
7ResNet50ImageNet Top-1 Accuracy63.6—Unverified
8ResNet50ImageNet Top-1 Accuracy61.5—Unverified
9ResNet50ImageNet Top-1 Accuracy61.5—Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3—Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1—Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77—Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55—Unverified