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 12011225 of 9051 papers

TitleStatusHype
ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic SegmentationCode1
Bias Loss for Mobile Neural NetworksCode1
Conditional Sound Generation Using Neural Discrete Time-Frequency Representation LearningCode1
General Virtual Sketching Framework for Vector Line ArtCode1
Adaptable Agent Populations via a Generative Model of PoliciesCode1
Tailor: Generating and Perturbing Text with Semantic ControlsCode1
COAST: COntrollable Arbitrary-Sampling NeTwork for Compressive SensingCode1
Generative and reproducible benchmarks for comprehensive evaluation of machine learning classifiersCode1
eProduct: A Million-Scale Visual Search Benchmark to Address Product Recognition ChallengesCode1
Fast Batch Nuclear-norm Maximization and Minimization for Robust Domain AdaptationCode1
Semi-Supervised Learning with Multi-Head Co-TrainingCode1
Diverse Video Generation using a Gaussian Process TriggerCode1
Wavelet Transform-assisted Adaptive Generative Modeling for ColorizationCode1
EEG-ConvTransformer for Single-Trial EEG based Visual Stimuli ClassificationCode1
Learning Invariant Representation with Consistency and Diversity for Semi-supervised Source Hypothesis TransferCode1
Keiki: Towards Realistic Danmaku Generation via Sequential GANsCode1
Controllable Open-ended Question Generation with A New Question Type OntologyCode1
Experience-Driven PCG via Reinforcement Learning: A Super Mario Bros StudyCode1
ResViT: Residual vision transformers for multi-modal medical image synthesisCode1
A Diverse Corpus for Evaluating and Developing English Math Word Problem SolversCode1
O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance LearningCode1
RAILS: A Robust Adversarial Immune-inspired Learning SystemCode1
UMIC: An Unreferenced Metric for Image Captioning via Contrastive LearningCode1
Neural Fashion Image Captioning : Accounting for Data DiversityCode1
Domain-Smoothing Network for Zero-Shot Sketch-Based Image RetrievalCode1
Show:102550
← PrevPage 49 of 363Next →

No leaderboard results yet.