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 341350 of 9051 papers

TitleStatusHype
Data Augmentation Alone Can Improve Adversarial TrainingCode1
Active Teacher for Semi-Supervised Object DetectionCode1
CtrSVDD: A Benchmark Dataset and Baseline Analysis for Controlled Singing Voice Deepfake DetectionCode1
Curiosity-Driven Reinforcement Learning from Human FeedbackCode1
Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-SpeechCode1
Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised SegmentationCode1
CrowdHuman: A Benchmark for Detecting Human in a CrowdCode1
Curriculum-guided Hindsight Experience ReplayCode1
Cross-Covariate Gait Recognition: A BenchmarkCode1
CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image SteganographyCode1
Show:102550
← PrevPage 35 of 906Next →

No leaderboard results yet.