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 676700 of 6661 papers

TitleStatusHype
CSGCL: Community-Strength-Enhanced Graph Contrastive LearningCode1
CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal ConversionCode1
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual RepresentationsCode1
Contrastive Learning for Cross-Domain Open World RecognitionCode1
Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated LearningCode1
CycleGuardian: A Framework for Automatic RespiratorySound classification Based on Improved Deep clustering and Contrastive LearningCode1
D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance AnnotationCode1
Contrastive Learning for Many-to-many Multilingual Neural Machine TranslationCode1
An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language ModelsCode1
Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the LeastCode1
Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport DistillationCode1
Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation OverlapCode1
DC-Seg: Disentangled Contrastive Learning for Brain Tumor Segmentation with Missing ModalitiesCode1
Debiased Contrastive LearningCode1
Debiased Contrastive Learning for Sequential RecommendationCode1
A Unified Generative Framework for Realistic Lidar Simulation in Autonomous Driving SystemsCode1
DeCLUTR: Deep Contrastive Learning for Unsupervised Textual RepresentationsCode1
Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot FillingCode1
Behavior Contrastive Learning for Unsupervised Skill DiscoveryCode1
Bridging Gaps: Federated Multi-View Clustering in Heterogeneous Hybrid ViewsCode1
AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive LearningCode1
Contrastive Learning for Cold-Start RecommendationCode1
Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based LossesCode1
A class-weighted supervised contrastive learning long-tailed bearing fault diagnosis approach using quadratic neural networkCode1
Contrastive Learning and Mixture of Experts Enables Precise Vector EmbeddingsCode1
Show:102550
← PrevPage 28 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