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 1301–1325 of 9051 papers

TitleStatusHype
DivAug: Plug-in Automated Data Augmentation with Explicit Diversity MaximizationCode1
Scaling-up Disentanglement for Image TranslationCode1
High-Fidelity Pluralistic Image Completion with TransformersCode1
Generating Novel Scene Compositions from Single Images and VideosCode1
Multimodal Motion Prediction with Stacked TransformersCode1
Local Patch AutoAugment with Multi-Agent CollaborationCode1
Large Scale Image Completion via Co-Modulated Generative Adversarial NetworksCode1
Beyond Trivial Counterfactual Explanations with Diverse Valuable ExplanationsCode1
Action detection using a neural network elucidates the genetics of mouse grooming behaviorCode1
Unconstrained Face-Mask & Face-Hand Datasets: Building a Computer Vision System to Help Prevent the Transmission of COVID-19Code1
DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial NetworkCode1
Modelling Behavioural Diversity for Learning in Open-Ended GamesCode1
Treatment Effect Estimation using Invariant Risk MinimizationCode1
Seeking the Shape of Sound: An Adaptive Framework for Learning Voice-Face AssociationCode1
Diverse Semantic Image Synthesis via Probability Distribution ModelingCode1
Topical Language Generation using TransformersCode1
When Face Recognition Meets Occlusion: A New BenchmarkCode1
Nutrition5k: Towards Automatic Nutritional Understanding of Generic FoodCode1
Group-wise Inhibition based Feature Regularization for Robust ClassificationCode1
GLAMOUR: Graph Learning over Macromolecule RepresentationsCode1
Multi-Objective Evolutionary Design of Composite Data-Driven ModelsCode1
Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial NetworksCode1
Mine Your Own vieW: Self-Supervised Learning Through Across-Sample PredictionCode1
How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative ModelsCode1
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual ConceptsCode1
Show:102550
← PrevPage 53 of 363Next →

No leaderboard results yet.