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 13511375 of 6661 papers

TitleStatusHype
Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-trainingCode1
DiffSim: Taming Diffusion Models for Evaluating Visual SimilarityCode1
Instance-aware Contrastive Learning for Occluded Human Mesh ReconstructionCode1
Contrastive Learning of Generalized Game RepresentationsCode1
Integrating multi-label contrastive learning with dual adversarial graph neural networks for cross-modal retrievalCode1
Contrastive learning of global and local features for medical image segmentation with limited annotationsCode1
Contrastive Learning of Global-Local Video RepresentationsCode1
Intent-aware Diffusion with Contrastive Learning for Sequential RecommendationCode1
Direct Preference-based Policy Optimization without Reward ModelingCode1
Contrastive Learning of Medical Visual Representations from Paired Images and TextCode1
Do Generated Data Always Help Contrastive Learning?Code1
Inter-Instance Similarity Modeling for Contrastive LearningCode1
CoT-BERT: Enhancing Unsupervised Sentence Representation through Chain-of-ThoughtCode1
Network Comparison with Interpretable Contrastive Network Representation LearningCode1
Contrastive Learning with Adversarial Perturbations for Conditional Text GenerationCode1
DetCo: Unsupervised Contrastive Learning for Object DetectionCode1
Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive LearningCode1
Contrastive Learning of Sentence Embeddings from ScratchCode1
An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language ModelsCode1
Contrastive Pretraining for Echocardiography Segmentation with Limited DataCode1
Jigsaw Clustering for Unsupervised Visual Representation LearningCode1
JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance DetectionCode1
Joint Contrastive Learning with Infinite PossibilitiesCode1
Joint Generative and Contrastive Learning for Unsupervised Person Re-identificationCode1
Compressive Visual RepresentationsCode1
Show:102550
← PrevPage 55 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