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 8001–8025 of 9051 papers

TitleStatusHype
DeepHuman: 3D Human Reconstruction from a Single ImageCode1
Dense Relational Captioning: Triple-Stream Networks for Relationship-Based CaptioningCode1
Superpixel-based Color Transfer—0
MirrorGAN: Learning Text-to-image Generation by RedescriptionCode0
Mode Seeking Generative Adversarial Networks for Diverse Image SynthesisCode0
Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural NetworksCode0
Individual-Level SNP Diversity and Similarity Profiles—0
Deep Generative Models: Deterministic Prediction with an Application in Inverse Rendering—0
Pluralistic Image CompletionCode0
GRATIS: GeneRAting TIme Series with diverse and controllable characteristicsCode0
Negative Training for Neural Dialogue Response GenerationCode0
Self-Supervised Learning of Face Representations for Video Face ClusteringCode0
Deep Generative Design: Integration of Topology Optimization and Generative Models—0
Jointly Optimizing Diversity and Relevance in Neural Response Generation—0
Multilingual Neural Machine Translation with Knowledge DistillationCode0
Ranking in Genealogy: Search Results Fusion at Ancestry—0
Unifying Ensemble Methods for Q-learning via Social Choice Theory—0
Improving Neural Response Diversity with Frequency-Aware Cross-Entropy LossCode0
Harmonizing Maximum Likelihood with GANs for Multimodal Conditional Generation—0
Lattice CNNs for Matching Based Chinese Question AnsweringCode1
On How Users Edit Computer-Generated Visual Stories—0
Diversity of Ensembles for Data Stream Classification—0
Operational Neural Networks—0
Guiding Neuroevolution with Structural Objectives—0
To Ensemble or Not Ensemble: When does End-To-End Training Fail?Code0
Show:102550
← PrevPage 321 of 363Next →

No leaderboard results yet.