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 1501–1525 of 9051 papers

TitleStatusHype
Context-Transformer: Tackling Object Confusion for Few-Shot DetectionCode1
Diversity can be Transferred: Output Diversification for White- and Black-box AttacksCode1
Learn to Augment: Joint Data Augmentation and Network Optimization for Text RecognitionCode1
AutoSTR: Efficient Backbone Search for Scene Text RecognitionCode1
Evaluating Logical Generalization in Graph Neural NetworksCode1
TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classificationCode1
Quality Diversity for Multi-task OptimizationCode1
An Empirical Investigation of Pre-Trained Transformer Language Models for Open-Domain Dialogue GenerationCode1
ProGen: Language Modeling for Protein GenerationCode1
Diverse and Admissible Trajectory Forecasting through Multimodal Context UnderstandingCode1
On the Role of Conceptualization in Commonsense Knowledge Graph ConstructionCode1
Combating noisy labels by agreement: A joint training method with co-regularizationCode1
Rethinking Parameter Counting in Deep Models: Effective Dimensionality RevisitedCode1
Data Augmentation using Pre-trained Transformer ModelsCode1
Scaling MAP-Elites to Deep NeuroevolutionCode1
Learning Texture Invariant Representation for Domain Adaptation of Semantic SegmentationCode1
Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene GraphsCode1
Analysis of diversity-accuracy tradeoff in image captioningCode1
PaDGAN: A Generative Adversarial Network for Performance Augmented Diverse DesignsCode1
PointAugment: an Auto-Augmentation Framework for Point Cloud ClassificationCode1
Reliable Fidelity and Diversity Metrics for Generative ModelsCode1
Towards Robust and Reproducible Active Learning Using Neural NetworksCode1
Sequential Latent Knowledge Selection for Knowledge-Grounded DialogueCode1
The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image ClassificationCode1
Self-Attentive Associative MemoryCode1
Show:102550
← PrevPage 61 of 363Next →

No leaderboard results yet.