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 1726–1750 of 6661 papers

TitleStatusHype
Negative Prototypes Guided Contrastive Learning for WSOD—0
RAG-based Crowdsourcing Task Decomposition via Masked Contrastive Learning with Prompts—0
MS-IMAP -- A Multi-Scale Graph Embedding Approach for Interpretable Manifold Learning—0
Towards Out-of-Distribution Detection in Vocoder Recognition via Latent Feature Reconstruction—0
Contrastive Language Video Time Pre-training—0
SMCL: Saliency Masked Contrastive Learning for Long-tailed Recognition—0
GOMAA-Geo: GOal Modality Agnostic Active Geo-localizationCode1
Personalized Topic Selection Model for Topic-Grounded Dialogue—0
DDA: Dimensionality Driven Augmentation Search for Contrastive Learning in Laparoscopic SurgeryCode0
Multi-Agent Transfer Learning via Temporal Contrastive Learning—0
Enhancing Inertial Hand based HAR through Joint Representation of Language, Pose and Synthetic IMUs—0
MGI: Multimodal Contrastive pre-training of Genomic and Medical Imaging—0
Unsupervised Contrastive Analysis for Salient Pattern Detection using Conditional Diffusion ModelsCode0
Contrastive Learning Via Equivariant Representation—0
Causal Contrastive Learning for Counterfactual Regression Over Time—0
Effectiveness of Vision Language Models for Open-world Single Image Test Time Adaptation—0
Heterophilous Distribution Propagation for Graph Neural Networks—0
Self-degraded contrastive domain adaptation for industrial fault diagnosis with bi-imbalanced data—0
Towards Spoken Language Understanding via Multi-level Multi-grained Contrastive Learning—0
LInK: Learning Joint Representations of Design and Performance Spaces through Contrastive Learning for Mechanism SynthesisCode1
Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation LearningCode0
Improving Paratope and Epitope Prediction by Multi-Modal Contrastive Learning and Interaction Informativeness EstimationCode0
Popularity-Aware Alignment and Contrast for Mitigating Popularity BiasCode0
GANcrop: A Contrastive Defense Against Backdoor Attacks in Federated Learning—0
Medication Recommendation via Dual Molecular Modalities and Multi-Step EnhancementCode0
Show:102550
← PrevPage 70 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