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 6301–6350 of 6661 papers

TitleStatusHype
URL: Combating Label Noise for Lung Nodule Malignancy GradingCode0
Rethinking Class-Incremental Learning from a Dynamic Imbalanced Learning PerspectiveCode0
3SD: Self-Supervised Saliency Detection With No LabelsCode0
Rethinking Contrastive Learning in Session-based RecommendationCode0
PARDON: Privacy-Aware and Robust Federated Domain GeneralizationCode0
GraphLearner: Graph Node Clustering with Fully Learnable AugmentationCode0
Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation LearningCode0
Calibrating Multi-modal Representations: A Pursuit of Group Robustness without AnnotationsCode0
Rethinking Graph Masked Autoencoders through Alignment and UniformityCode0
Fine-grained Contrastive Learning for Definition GenerationCode0
CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive LearningCode0
Fine-grained Contrastive Learning for Relation ExtractionCode0
Fine-grained Background Representation for Weakly Supervised Semantic SegmentationCode0
Finding "Good Views" of Electrocardiogram Signals for Inferring Abnormalities in Cardiac ConditionCode0
An Empirical Study of Accuracy-Robustness Tradeoff and Training Efficiency in Self-Supervised LearningCode0
Integrating Prior Knowledge in Contrastive Learning with KernelCode0
Bundle Recommendation with Item-level Causation-enhanced Multi-view LearningCode0
Few-Shot Segmentation with Global and Local Contrastive LearningCode0
An efficient framework based on large foundation model for cervical cytopathology whole slide image screeningCode0
Few-Shot Electronic Health Record Coding through Graph Contrastive LearningCode0
Few-Max: Few-Shot Domain Adaptation for Unsupervised Contrastive Representation LearningCode0
UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed EntitiesCode0
FESS Loss: Feature-Enhanced Spatial Segmentation Loss for Optimizing Medical Image AnalysisCode0
Contrastive Corpus Attribution for Explaining RepresentationsCode0
Rethinking Temperature in Graph Contrastive LearningCode0
Rethinking the Augmentation Module in Contrastive Learning: Learning Hierarchical Augmentation Invariance with Expanded ViewsCode0
FedStyle: Style-Based Federated Learning Crowdsourcing Framework for Art CommissionsCode0
Contrastive Attraction and Contrastive Repulsion for Representation LearningCode0
FedSKC: Federated Learning with Non-IID Data via Structural Knowledge CollaborationCode0
Supervised Stochastic Neighbor Embedding Using Contrastive LearningCode0
FedSC: Federated Learning with Semantic-Aware CollaborationCode0
Anatomy-Aware Contrastive Representation Learning for Fetal UltrasoundCode0
USE: Dynamic User Modeling with Stateful Sequence ModelsCode0
Contrastive Conditional Latent Diffusion for Audio-visual SegmentationCode0
FedPCL-CDR: A Federated Prototype-based Contrastive Learning Framework for Privacy-Preserving Cross-domain RecommendationCode0
Features Based Adaptive Augmentation for Graph Contrastive LearningCode0
Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised LearningCode0
Feature-Level Debiased Natural Language UnderstandingCode0
Unbiased and Efficient Self-Supervised Incremental Contrastive LearningCode0
Self-supervised Feature-Gate Coupling for Dynamic Network PruningCode0
Unbiased and Robust: External Attention-enhanced Graph Contrastive Learning for Cross-domain Sequential RecommendationCode0
Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation LearningCode0
Contrastive Bi-Projector for Unsupervised Domain AdaptionCode0
SurANet: Surrounding-Aware Network for Concealed Object Detection via Highly-Efficient Interactive Contrastive Learning StrategyCode0
Contrastive-Based Deep Embeddings for Label Noise-Resilient Histopathology Image ClassificationCode0
Revealing Vision-Language Integration in the Brain with Multimodal NetworksCode0
FBA-Net: Foreground and Background Aware Contrastive Learning for Semi-Supervised Atrium SegmentationCode0
Surrogate- and invariance-boosted contrastive learning for data-scarce applications in scienceCode0
Revisiting 3D ResNets for Video RecognitionCode0
Revisiting and Benchmarking Graph Autoencoders: A Contrastive Learning PerspectiveCode0
Show:102550
← PrevPage 127 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