SOTAVerified

Diversity

Diversity in data sampling is crucial across various use cases, including search, recommendation systems, and more. Ensuring diverse samples means capturing a wide range of variations and perspectives, which leads to more robust, unbiased, and comprehensive models. In search use cases, for instance, diversity helps avoid redundancy, ensuring that users are exposed to a broader set of relevant information rather than repeated similar results.

Papers

Showing 27212730 of 9051 papers

TitleStatusHype
BSDA: Bayesian Random Semantic Data Augmentation for Medical Image ClassificationCode0
LLaVA-VSD: Large Language-and-Vision Assistant for Visual Spatial DescriptionCode0
Federated Visual Classification with Real-World Data DistributionCode0
LLMs for Extremely Low-Resource Finno-Ugric LanguagesCode0
FedCCRL: Federated Domain Generalization with Cross-Client Representation LearningCode0
Anomaly Detection in Video Sequence with Appearance-Motion CorrespondenceCode0
Bayesian Prediction of Future Street Scenes using Synthetic LikelihoodsCode0
Federated Neural Topic ModelsCode0
Federated Stain Normalization for Computational PathologyCode0
Feasible Recourse Plan via Diverse InterpolationCode0
Show:102550
← PrevPage 273 of 906Next →

No leaderboard results yet.