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 651660 of 9051 papers

TitleStatusHype
BiRT: Bio-inspired Replay in Vision Transformers for Continual LearningCode1
Diverse Image Captioning with Context-Object Split Latent SpacesCode1
A Doubly Decoupled Network for edge detectionCode1
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask LearningCode1
An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language ModelsCode1
Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary SpaceCode1
BLEU might be Guilty but References are not InnocentCode1
An Informative Tracking BenchmarkCode1
DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking TasksCode1
Diverse Image Generation via Self-Conditioned GANsCode1
Show:102550
← PrevPage 66 of 906Next →

No leaderboard results yet.