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 5226–5250 of 6661 papers

TitleStatusHype
Improve Unsupervised Pretraining for Few-label Transfer—0
Improving Abstractive Dialogue Summarization with Speaker-Aware Supervised Contrastive Learning—0
Improving Abstractive Dialogue Summarization with Speaker-Aware Supervised Contrastive Learning—0
Improving Anomaly Segmentation with Multi-Granularity Cross-Domain Alignment—0
Improving classification of road surface conditions via road area extraction and contrastive learning—0
Improving Content Recommendation: Knowledge Graph-Based Semantic Contrastive Learning for Diversity and Cold-Start Users—0
Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning—0
Improving Continual Relation Extraction through Prototypical Contrastive Learning—0
Improving Contrastive Learning on Visually Homogeneous Mars Rover Images—0
Improving COVID-19 CT Classification of CNNs by Learning Parameter-Efficient Representation—0
Improving Cross-Modal Understanding in Visual Dialog via Contrastive Learning—0
Improving Deep Embedded Clustering via Learning Cluster-level Representations—0
Improving Dense Contrastive Learning with Dense Negative Pairs—0
Improving Dialog Safety using Socially Aware Contrastive Learning—0
Improving Disease Detection from Social Media Text via Self-Augmentation and Contrastive Learning—0
Improving Event Temporal Relation Classification via Auxiliary Label-Aware Contrastive Learning—0
Improving Factuality of Abstractive Summarization via Contrastive Reward Learning—0
Improving Generalizability of Protein Sequence Models via Data Augmentations—0
Improving Gradient-based Adversarial Training for Text Classification by Contrastive Learning and Auto-Encoder—0
Improving Graph Contrastive Learning via Adaptive Positive Sampling—0
Improving Long Tailed Document-Level Relation Extraction via Easy Relation Augmentation and Contrastive Learning—0
Improving Micro-video Recommendation by Controlling Position Bias—0
Improving Multi-Label Contrastive Learning by Leveraging Label Distribution—0
Improving Multimodal Sentiment Analysis: Supervised Angular Margin-based Contrastive Learning for Enhanced Fusion Representation—0
Improving Neural Topic Models by Contrastive Learning with BERT—0
Show:102550
← PrevPage 210 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