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 36613670 of 9051 papers

TitleStatusHype
Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active LearningCode0
LesionMix: A Lesion-Level Data Augmentation Method for Medical Image SegmentationCode0
Diversifying AI: Towards Creative Chess with AlphaZero0
Globe230k: A Benchmark Dense-Pixel Annotation Dataset for Global Land Cover Mapping0
Flickr Africa: Examining Geo-Diversity in Large-Scale, Human-Centric Visual Data0
Non-monotone Sequential Submodular Maximization0
Lightweight Adaptation of Neural Language Models via Subspace EmbeddingCode0
Diff-CAPTCHA: An Image-based CAPTCHA with Security Enhanced by Denoising Diffusion Model0
Ranking-aware Uncertainty for Text-guided Image Retrieval0
Learning from All Sides: Diversified Positive Augmentation via Self-distillation in Recommendation0
Show:102550
← PrevPage 367 of 906Next →

No leaderboard results yet.