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

Showing 21512175 of 6661 papers

TitleStatusHype
MG-3D: Multi-Grained Knowledge-Enhanced 3D Medical Vision-Language Pre-trainingCode0
Data Efficient Contrastive Learning in Histopathology using Active SamplingCode0
Meta-GPS++: Enhancing Graph Meta-Learning with Contrastive Learning and Self-TrainingCode0
A Contrastive Learning Approach to Mitigate Bias in Speech ModelsCode0
Data Cleansing with Contrastive Learning for Vocal Note Event AnnotationsCode0
Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric VideosCode0
Data Augmentation for Compositional Data: Advancing Predictive Models of the MicrobiomeCode0
MeDSLIP: Medical Dual-Stream Language-Image Pre-training for Fine-grained AlignmentCode0
Multi-task Meta Label Correction for Time Series PredictionCode0
CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous QueriesCode0
MEDFORM: A Foundation Model for Contrastive Learning of CT Imaging and Clinical Numeric Data in Multi-Cancer AnalysisCode0
Medical Question Summarization with Entity-driven Contrastive LearningCode0
MCRL4OR: Multimodal Contrastive Representation Learning for Off-Road Environmental PerceptionCode0
CLAP. I. Resolving miscalibration for deep learning-based galaxy photometric redshift estimationCode0
Medication Recommendation via Dual Molecular Modalities and Multi-Step EnhancementCode0
MetaCOVID: A Siamese neural network framework with contrastive loss for n-shot diagnosis of COVID-19 patientsCode0
MassNet: A Deep Learning Approach for Body Weight Extraction from A Single Pressure ImageCode0
CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in SegmentationCode0
A Generalizable Deep Learning System for Cardiac MRICode0
Mask-Guided Contrastive Attention Model for Person Re-IdentificationCode0
Masked Student Dataset of ExpressionsCode0
Mask-informed Deep Contrastive Incomplete Multi-view ClusteringCode0
Customized Retrieval Augmented Generation and Benchmarking for EDA Tool Documentation QACode0
Masking Improves Contrastive Self-Supervised Learning for ConvNets, and Saliency Tells You WhereCode0
Multi-Level Sequence Denoising with Cross-Signal Contrastive Learning for Sequential RecommendationCode0
Show:102550
← PrevPage 87 of 267Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6Unverified
2ResNet50ImageNet Top-1 Accuracy73Unverified
3ResNet50ImageNet Top-1 Accuracy71.1Unverified
4ResNet50ImageNet Top-1 Accuracy69.3Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8Unverified
7ResNet50ImageNet Top-1 Accuracy63.6Unverified
8ResNet50ImageNet Top-1 Accuracy61.5Unverified
9ResNet50ImageNet Top-1 Accuracy61.5Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55Unverified