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 1251–1275 of 9051 papers

TitleStatusHype
Transforming the Latent Space of StyleGAN for Real Face EditingCode1
The Herbarium 2021 Half-Earth Challenge DatasetCode1
ResT: An Efficient Transformer for Visual RecognitionCode1
Synthetic Data Generation for Grammatical Error Correction with Tagged Corruption ModelsCode1
ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learningCode1
Bilingual Mutual Information Based Adaptive Training for Neural Machine TranslationCode1
One2Set: Generating Diverse Keyphrases as a SetCode1
Improving Contrastive Learning on Imbalanced Data via Open-World SamplingCode1
Profiling Pareto Front With Multi-Objective Stein Variational Gradient DescentCode1
An Empirical Study of Vehicle Re-Identification on the AI City ChallengeCode1
Contrastive Model Inversion for Data-Free Knowledge DistillationCode1
Plot and Rework: Modeling Storylines for Visual StorytellingCode1
Semantic Diversity Learning for Zero-Shot Multi-label ClassificationCode1
Learning to Generate Novel Scene Compositions from Single Images and VideosCode1
Improving Adversarial Transferability with Gradient RefiningCode1
Stochastic Image-to-Video Synthesis using cINNsCode1
Recommendations for Item Set Completion: On the Semantics of Item Co-Occurrence With Data Sparsity, Input Size, and Input ModalitiesCode1
SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of ExpertsCode1
PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose EstimationCode1
Meta-Learning-Based Deep Reinforcement Learning for Multiobjective Optimization ProblemsCode1
PD-GAN: Probabilistic Diverse GAN for Image InpaintingCode1
The Tracking Machine Learning challenge : Throughput phaseCode1
Few-Shot Video Object DetectionCode1
Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space EmbeddingCode1
LasHeR: A Large-scale High-diversity Benchmark for RGBT TrackingCode1
Show:102550
← PrevPage 51 of 363Next →

No leaderboard results yet.