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 1501–1525 of 6661 papers

TitleStatusHype
Self-supervised transformer-based pre-training method with General Plant Infection datasetCode0
Advancing Melanoma Diagnosis with Self-Supervised Neural Networks: Evaluating the Effectiveness of Different Techniques—0
Semi-supervised reference-based sketch extraction using a contrastive learning frameworkCode1
Contrastive Learning with Counterfactual Explanations for Radiology Report Generation—0
Self-Supervised Video Representation Learning in a Heuristic Decoupled Perspective—0
Double Gradient Reversal Network for Single-Source Domain Generalization in Multi-mode Fault Diagnosis—0
L^2CL: Embarrassingly Simple Layer-to-Layer Contrastive Learning for Graph Collaborative FilteringCode0
ETSCL: An Evidence Theory-Based Supervised Contrastive Learning Framework for Multi-modal Glaucoma GradingCode0
Improving classification of road surface conditions via road area extraction and contrastive learning—0
Semi-Supervised Contrastive Learning of Musical RepresentationsCode1
Keypoint Aware Masked Image ModellingCode0
X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs—0
LIDIA: Precise Liver Tumor Diagnosis on Multi-Phase Contrast-Enhanced CT via Iterative Fusion and Asymmetric Contrastive Learning—0
Open-World Electrocardiogram Classification via Domain Knowledge-Driven Contrastive LearningCode1
Mutual Information Guided Optimal Transport for Unsupervised Visible-Infrared Person Re-identification—0
Subgraph-Aware Training of Language Models for Knowledge Graph Completion Using Structure-Aware Contrastive LearningCode0
CDFL: Efficient Federated Human Activity Recognition using Contrastive Learning and Deep Clustering—0
Causality-inspired Discriminative Feature Learning in Triple Domains for Gait Recognition—0
Continual Learning for Temporal-Sensitive Question Answering—0
Progressive Proxy Anchor Propagation for Unsupervised Semantic SegmentationCode1
Overfitting In Contrastive Learning?—0
Video-Language Alignment via Spatio-Temporal Graph TransformerCode1
Cycle Contrastive Adversarial Learning for Unsupervised image Deraining—0
Relational Representation DistillationCode1
An efficient framework based on large foundation model for cervical cytopathology whole slide image screeningCode0
Show:102550
← PrevPage 61 of 267Next →
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