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 851860 of 9051 papers

TitleStatusHype
Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose EstimationCode1
G-Eval: NLG Evaluation using GPT-4 with Better Human AlignmentCode1
PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation LayoutCode1
Image Quality-aware Diagnosis via Meta-knowledge Co-embeddingCode1
KPEval: Towards Fine-Grained Semantic-Based Keyphrase EvaluationCode1
VisDA 2022 Challenge: Domain Adaptation for Industrial Waste SortingCode1
Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning ParadigmCode1
Towards Diverse and Coherent Augmentation for Time-Series ForecastingCode1
TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo SupervisionCode1
Take 5: Interpretable Image Classification with a Handful of FeaturesCode1
Show:102550
← PrevPage 86 of 906Next →

No leaderboard results yet.