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 4501–4525 of 6661 papers

TitleStatusHype
Manifold Contrastive Learning with Variational Lie Group OperatorsCode0
Online Unsupervised Video Object Segmentation via Contrastive Motion ClusteringCode0
What Constitutes Good Contrastive Learning in Time-Series Forecasting?Code0
Contrastive Disentangled Learning on Graph for Node Classification—0
Understanding Contrastive Learning Through the Lens of Margins—0
Deep Double Self-Expressive Subspace ClusteringCode0
M3PT: A Multi-Modal Model for POI Tagging—0
Crowdsourcing and Evaluating Text-Based Audio Retrieval RelevancesCode0
Label-noise-tolerant medical image classification via self-attention and self-supervised learning—0
CMLM-CSE: Based on Conditional MLM Contrastive Learning for Sentence Embeddings—0
Description-Enhanced Label Embedding Contrastive Learning for Text ClassificationCode0
Learning on Graphs under Label Noise—0
Fine-Tuned but Zero-Shot 3D Shape Sketch View Similarity and Retrieval—0
Enhanced Multimodal Representation Learning with Cross-modal KD—0
GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition—0
CARL-G: Clustering-Accelerated Representation Learning on Graphs—0
Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient EncoderCode0
A Pairing Enhancement Approach for Aspect Sentiment Triplet Extraction—0
Securing Visually-Aware Recommender Systems: An Adversarial Image Reconstruction and Detection Framework—0
Liquidity takers behavior representation through a contrastive learning approach—0
Contrastive Learning for Predicting Cancer Prognosis Using Gene Expression ValuesCode0
Regularizing with Pseudo-Negatives for Continual Self-Supervised LearningCode0
A brief review of contrastive learning applied to astrophysics—0
Variable Radiance Field for Real-Life Category-Specifc Reconstruction from Single Image—0
CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification—0
Show:102550
← PrevPage 181 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