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 10011010 of 9051 papers

TitleStatusHype
DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific DeltaCode1
Continual Variational Autoencoder Learning via Online Cooperative MemorizationCode1
Controllable and Guided Face Synthesis for Unconstrained Face RecognitionCode1
Difficulty-Aware Simulator for Open Set RecognitionCode1
DH-AUG: DH Forward Kinematics Model Driven Augmentation for 3D Human Pose EstimationCode1
Towards Diverse and Faithful One-shot Adaption of Generative Adversarial NetworksCode1
FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANsCode1
Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary SpaceCode1
Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text GenerationCode1
DGPO: Discovering Multiple Strategies with Diversity-Guided Policy OptimizationCode1
Show:102550
← PrevPage 101 of 906Next →

No leaderboard results yet.