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 3601–3650 of 6661 papers

TitleStatusHype
Features-over-the-Air: Contrastive Learning Enabled Cooperative Edge Inference—0
DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP TrainingCode1
PerCoNet: News Recommendation with Explicit Persona and Contrastive Learning—0
Multimodal Short Video Rumor Detection System Based on Contrastive Learning—0
H2CGL: Modeling Dynamics of Citation Network for Impact PredictionCode1
Harnessing Contrastive Learning and Neural Transformation for Time Series Anomaly Detection—0
Meta-optimized Contrastive Learning for Sequential RecommendationCode1
Hierarchical and Contrastive Representation Learning for Knowledge-aware Recommendation—0
MvCo-DoT:Multi-View Contrastive Domain Transfer Network for Medical Report Generation—0
Medical Question Summarization with Entity-driven Contrastive LearningCode0
BCE-Net: Reliable Building Footprints Change Extraction based on Historical Map and Up-to-Date Images using Contrastive LearningCode1
CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category DiscoveryCode0
Covidia: COVID-19 Interdisciplinary Academic Knowledge Graph—0
Robust Multiview Multimodal Driver Monitoring System Using Masked Multi-Head Self-AttentionCode0
Verbs in Action: Improving verb understanding in video-language modelsCode0
CLCLSA: Cross-omics Linked embedding with Contrastive Learning and Self Attention for multi-omics integration with incomplete multi-omics data—0
RECLIP: Resource-efficient CLIP by Training with Small Images—0
Learning Transferable Pedestrian Representation from Multimodal Information SupervisionCode0
Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning—0
Semi-Supervised Relational Contrastive Learning—0
Sentence-Level Relation Extraction via Contrastive Learning with Descriptive Relation Prompts—0
Triple Sequence Learning for Cross-domain Recommendation—0
Investigating Graph Structure Information for Entity Alignment with Dangling Cases—0
Delving into E-Commerce Product Retrieval with Vision-Language Pre-training—0
OpenDriver: An Open-Road Driver State Detection DatasetCode0
Continual Graph Convolutional Network for Text ClassificationCode0
Self-Supervised Learning of Object Segmentation from Unlabeled RGB-D Videos—0
The Short Text Matching Model Enhanced with Knowledge via Contrastive Learning—0
Attack-Augmentation Mixing-Contrastive Skeletal Representation LearningCode0
On the Importance of Contrastive Loss in Multimodal Learning—0
Multilingual Augmentation for Robust Visual Question Answering in Remote Sensing Images—0
Supervised Contrastive Learning with Heterogeneous Similarity for Distribution Shifts—0
Masked Student Dataset of ExpressionsCode0
Linking Representations with Multimodal Contrastive Learning—0
Anomalous Sound Detection using Audio Representation with Machine ID based Contrastive Learning Pretraining—0
Localized Region Contrast for Enhancing Self-Supervised Learning in Medical Image Segmentation—0
Evidentiality-aware Retrieval for Overcoming Abstractiveness in Open-Domain Question Answering—0
Unraveling Instance Associations: A Closer Look for Audio-Visual SegmentationCode1
Synthetic Hard Negative Samples for Contrastive Learning—0
ACTION++: Improving Semi-supervised Medical Image Segmentation with Adaptive Anatomical ContrastCode1
Adaptive Data Augmentation for Contrastive Learning—0
Detecting and Grounding Multi-Modal Media ManipulationCode2
A Unified Contrastive Transfer Framework with Propagation Structure for Boosting Low-Resource Rumor Detection—0
Black Box Few-Shot Adaptation for Vision-Language modelsCode1
PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification—0
Learning Invariant Representation via Contrastive Feature Alignment for Clutter Robust SAR Target Recognition—0
Multi-Level Contrastive Learning for Dense Prediction TaskCode0
Towards Integration of Discriminability and Robustness for Document-Level Relation ExtractionCode0
Multi-Modal Representation Learning with Text-Driven Soft Masks—0
RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene UnderstandingCode2
Show:102550
← PrevPage 73 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