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 6251–6300 of 6661 papers

TitleStatusHype
Contrastive Learning and Adversarial Disentanglement for Task-Oriented Semantic CommunicationsCode0
Unsupervised Word Alignment via Cross-Lingual Contrastive LearningCode0
Can Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions?Code0
Relation Extraction with Weighted Contrastive Pre-training on Distant SupervisionCode0
Can Machines Resonate with Humans? Evaluating the Emotional and Empathic Comprehension of LMsCode0
From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model CompressionCode0
Contrastive Latent Variable Models for Neural Text GenerationCode0
Contrastive Knowledge Graph Error DetectionCode0
FPPL: An Efficient and Non-IID Robust Federated Continual Learning FrameworkCode0
Forensic Histopathological Recognition via a Context-Aware MIL Network Powered by Self-Supervised Contrastive LearningCode0
Reliable Node Similarity Matrix Guided Contrastive Graph ClusteringCode0
Reliable Pseudo-labeling via Optimal Transport with Attention for Short Text ClusteringCode0
Superpixel Graph Contrastive Clustering with Semantic-Invariant Augmentations for Hyperspectral ImagesCode0
Contrastive Instruction-Trajectory Learning for Vision-Language NavigationCode0
Statement-Level Vulnerability Detection: Learning Vulnerability Patterns Through Information Theory and Contrastive LearningCode0
Supervised Contrastive CSI Representation Learning for Massive MIMO PositioningCode0
Removing Geometric Bias in One-Class Anomaly Detection with Adaptive Feature PerturbationCode0
FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical LearningCode0
FontGuard: A Robust Font Watermarking Approach Leveraging Deep Font KnowledgeCode0
Contrastive Instance Association for 4D Panoptic Segmentation using Sequences of 3D LiDAR ScansCode0
An Information Minimization Based Contrastive Learning Model for Unsupervised Sentence Embeddings LearningCode0
Unveiling interpretable development-specific gene signatures in the developing human prefrontal cortex with ICGSCode0
ADS-Cap: A Framework for Accurate and Diverse Stylized Captioning with Unpaired Stylistic CorporaCode0
ContrastiveGaussian: High-Fidelity 3D Generation with Contrastive Learning and Gaussian SplattingCode0
Focus on Focus: Focus-oriented Representation Learning and Multi-view Cross-modal Alignment for Glioma GradingCode0
Supervised Contrastive Learning for Interpretable Long-Form Document MatchingCode0
Contrastive Enhanced Slide Filter Mixer for Sequential RecommendationCode0
Representation Learning via Consistent Assignment of Views to ClustersCode0
Focus-Driven Contrastive Learniang for Medical Question SummarizationCode0
Unveiling Large Language Models Generated Texts: A Multi-Level Fine-Grained Detection FrameworkCode0
Contrastive Embedding Distribution Refinement and Entropy-Aware Attention for 3D Point Cloud ClassificationCode0
FlowCon: Out-of-Distribution Detection using Flow-Based Contrastive LearningCode0
TwinCL: A Twin Graph Contrastive Learning Model for Collaborative FilteringCode0
Supervised Contrastive Learning for Affect ModellingCode0
Camera-Tracklet-Aware Contrastive Learning for Unsupervised Vehicle Re-IdentificationCode0
Camera Alignment and Weighted Contrastive Learning for Domain Adaptation in Video Person ReIDCode0
An Eye for an Ear: Zero-shot Audio Description Leveraging an Image Captioner using Audiovisual Distribution AlignmentCode0
FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive ModelsCode0
WACO: Word-Aligned Contrastive Learning for Speech TranslationCode0
Resolving Lexical Bias in Edit Scoping with Projector Editor NetworksCode0
Fine-Grained Representation Learning via Multi-Level Contrastive Learning without Class PriorsCode0
Flexible Phase Dynamics for Bio-Plausible Contrastive LearningCode0
CoDeGAN: Contrastive Disentanglement for Generative Adversarial NetworkCode0
A Contrastive Learning Approach to Mitigate Bias in Speech ModelsCode0
When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive LearningCode0
Calibration-based Dual Prototypical Contrastive Learning Approach for Domain Generalization Semantic SegmentationCode0
Rethinking 360deg Image Visual Attention Modelling With Unsupervised Learning.Code0
FISHing in Uncertainty: Synthetic Contrastive Learning for Genetic Aberration DetectionCode0
Rethinking and Simplifying Bootstrapped Graph LatentsCode0
An Experimental Comparison Of Multi-view Self-supervised Methods For Music TaggingCode0
Show:102550
← PrevPage 126 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