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 841850 of 9051 papers

TitleStatusHype
Shape-Erased Feature Learning for Visible-Infrared Person Re-IdentificationCode1
Zero-shot Generative Model Adaptation via Image-specific Prompt LearningCode1
Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen DomainsCode1
Industrial Anomaly Detection with Domain Shift: A Real-world Dataset and Masked Multi-scale ReconstructionCode1
Efficient OCR for Building a Diverse Digital HistoryCode1
SLPerf: a Unified Framework for Benchmarking Split LearningCode1
DivClust: Controlling Diversity in Deep ClusteringCode1
DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking TasksCode1
The Archive Query Log: Mining Millions of Search Result Pages of Hundreds of Search Engines from 25 Years of Web ArchivesCode1
A View From Somewhere: Human-Centric Face RepresentationsCode1
Show:102550
← PrevPage 85 of 906Next →

No leaderboard results yet.