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 27512775 of 6661 papers

TitleStatusHype
Event-Based Contrastive Learning for Medical Time SeriesCode0
Contrasting quadratic assignments for set-based representation learningCode0
L^2CL: Embarrassingly Simple Layer-to-Layer Contrastive Learning for Graph Collaborative FilteringCode0
Knowledge-aware Dual-side Attribute-enhanced RecommendationCode0
Bayesian Self-Supervised Contrastive LearningCode0
Evaluating Large Language Models for Phishing Detection, Self-Consistency, Faithfulness, and ExplainabilityCode0
Bayesian Robust Graph Contrastive LearningCode0
Knowing Where and What: Unified Word Block Pretraining for Document UnderstandingCode0
ETSCL: An Evidence Theory-Based Supervised Contrastive Learning Framework for Multi-modal Glaucoma GradingCode0
AmorLIP: Efficient Language-Image Pretraining via AmortizationCode0
Estimated Audio-Caption Correspondences Improve Language-Based Audio RetrievalCode0
Keypoint Aware Masked Image ModellingCode0
Establishing a stronger baseline for lightweight contrastive modelsCode0
Reducing Predictive Feature Suppression in Resource-Constrained Contrastive Image-Caption RetrievalCode0
Key Point Analysis via Contrastive Learning and Extractive Argument SummarizationCode0
Less is More: Multimodal Region Representation via Pairwise Inter-view LearningCode0
Joint Prediction of Meningioma Grade and Brain Invasion via Task-Aware Contrastive LearningCode0
Joint Representation Learning for Text and 3D Point CloudCode0
Contrast and Clustering: Learning Neighborhood Pair Representation for Source-free Domain AdaptationCode0
Joint Searching and Grounding: Multi-Granularity Video Content RetrievalCode0
An Analysis of Robustness of Non-Lipschitz NetworksCode0
Equivariant Contrastive Learning for Sequential RecommendationCode0
Joint Masked Reconstruction and Contrastive Learning for Mining Interactions Between ProteinsCode0
On the Role of Discrete Tokenization in Visual Representation LearningCode0
EqCo: Equivalent Rules for Self-supervised Contrastive LearningCode0
Show:102550
← PrevPage 111 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