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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 351–375 of 9051 papers

TitleStatusHype
A View From Somewhere: Human-Centric Face RepresentationsCode1
Deep Color Transfer using Histogram AnalogyCode1
Active learning for medical image segmentation with stochastic batchesCode1
Grounding Language to Autonomously-Acquired Skills via Goal GenerationCode1
Deep Diversity-Enhanced Feature Representation of Hyperspectral ImagesCode1
DATED: Guidelines for Creating Synthetic Datasets for Engineering Design ApplicationsCode1
Dataset GrowthCode1
DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector QuantizationCode1
AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker DetectionCode1
AbGPT: De Novo Antibody Design via Generative Language ModelingCode1
Dataset Factorization for CondensationCode1
Decoding Matters: Addressing Amplification Bias and Homogeneity Issue for LLM-based RecommendationCode1
Deep Encoder-Decoder Networks for Classification of Hyperspectral and LiDAR DataCode1
Active Learning by Acquiring Contrastive ExamplesCode1
Data Augmentation Alone Can Improve Adversarial TrainingCode1
Data Augmentation Approaches in Natural Language Processing: A SurveyCode1
Automating Rigid Origami DesignCode1
Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning ParadigmCode1
DART: Articulated Hand Model with Diverse Accessories and Rich TexturesCode1
Data Augmentation using Pre-trained Transformer ModelsCode1
Active Domain Adaptation via Clustering Uncertainty-weighted EmbeddingsCode1
Dance with You: The Diversity Controllable Dancer Generation via Diffusion ModelsCode1
Dan: Deep attention neural network for news recommendationCode1
AutoMix: Automatically Mixing Language ModelsCode1
Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problemCode1
Show:102550
← PrevPage 15 of 363Next →

No leaderboard results yet.