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 15711580 of 9051 papers

TitleStatusHype
Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine LearningCode1
COVIDx CT-3: A Large-scale, Multinational, Open-Source Benchmark Dataset for Computer-aided COVID-19 Screening from Chest CT ImagesCode1
ResViT: Residual vision transformers for multi-modal medical image synthesisCode1
Rethinking Data Augmentation for Single-source Domain Generalization in Medical Image SegmentationCode1
Rethinking HTG Evaluation: Bridging Generation and RecognitionCode1
Rethinking Image Super-Resolution from Training Data PerspectivesCode1
Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised SegmentationCode1
Rethinking Parameter Counting in Deep Models: Effective Dimensionality RevisitedCode1
Revealing the Dark Secrets of Masked Image ModelingCode1
DALDA: Data Augmentation Leveraging Diffusion Model and LLM with Adaptive Guidance ScalingCode1
Show:102550
← PrevPage 158 of 906Next →

No leaderboard results yet.