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 1926–1950 of 6661 papers

TitleStatusHype
Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table RepresentationsCode0
TrACT: A Training Dynamics Aware Contrastive Learning Framework for Long-tail Trajectory Prediction—0
When LLMs are Unfit Use FastFit: Fast and Effective Text Classification with Many ClassesCode3
Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate RainsCode0
An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-TrainingCode2
FecTek: Enhancing Term Weight in Lexicon-Based Retrieval with Feature Context and Term-level Knowledge—0
Knowledge-Aware Multi-Intent Contrastive Learning for Multi-Behavior Recommendation—0
Blind Localization and Clustering of Anomalies in TexturesCode1
Reuse out-of-year data to enhance land cover mappingvia feature disentanglement and contrastive learning—0
Multimodal 3D Object Detection on Unseen Domains—0
Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and NegativesCode1
DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time SeriesCode1
Single-temporal Supervised Remote Change Detection for Domain Generalization—0
InfoMatch: Entropy Neural Estimation for Semi-Supervised Image ClassificationCode1
Supervised Contrastive Vision Transformer for Breast Histopathological Image Classification—0
EMC^2: Efficient MCMC Negative Sampling for Contrastive Learning with Global ConvergenceCode0
Vision-and-Language Navigation via Causal LearningCode2
Contextrast: Contextual Contrastive Learning for Semantic Segmentation—0
Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation—0
Digging into contrastive learning for robust depth estimation with diffusion modelsCode1
WB LUTs: Contrastive Learning for White Balancing Lookup TablesCode1
Unsupervised Federated Optimization at the Edge: D2D-Enabled Learning without Labels—0
RankCLIP: Ranking-Consistent Language-Image PretrainingCode1
Learning Tracking Representations from Single Point Annotations—0
Contrastive Mean-Shift Learning for Generalized Category Discovery—0
Show:102550
← PrevPage 78 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