Copertina

Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hemmat, Reyhane Askari, Hall, Melissa, Sun, Alicia, Ross, Candace, Drozdzal, Michal, Romero-Soriano, Adriana
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Multi-Modal Language Models as Text-to-Image Model Evaluators
di: Chen, Jiahui, et al.
Pubblicazione: (2025)

Increasing the Utility of Synthetic Images through Chamfer Guidance
di: Dall'Asen, Nicola, et al.
Pubblicazione: (2025)

Feedback-guided Data Synthesis for Imbalanced Classification
di: Hemmat, Reyhane Askari, et al.
Pubblicazione: (2023)

DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity
di: Hall, Melissa, et al.
Pubblicazione: (2023)

Improving the Physics of Video Generation with VJEPA-2 Reward Signal
di: Yuan, Jianhao, et al.
Pubblicazione: (2025)

Inference-time Physics Alignment of Video Generative Models with Latent World Models
di: Yuan, Jianhao, et al.
Pubblicazione: (2026)

Towards Geographic Inclusion in the Evaluation of Text-to-Image Models
di: Hall, Melissa, et al.
Pubblicazione: (2024)

On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
di: Ifriqi, Tariq Berrada, et al.
Pubblicazione: (2024)

EvalGIM: A Library for Evaluating Generative Image Models
di: Hall, Melissa, et al.
Pubblicazione: (2024)

Improving Text-to-Image Consistency via Automatic Prompt Optimization
di: Mañas, Oscar, et al.
Pubblicazione: (2024)

Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image
di: Hu, Yushi, et al.
Pubblicazione: (2025)

Unified Text-Image Generation with Weakness-Targeted Post-Training
di: Chen, Jiahui, et al.
Pubblicazione: (2026)

Improving the Scaling Laws of Synthetic Data with Deliberate Practice
di: Askari-Hemmat, Reyhane, et al.
Pubblicazione: (2025)

Consistency-diversity-realism Pareto fronts of conditional image generative models
di: Astolfi, Pietro, et al.
Pubblicazione: (2024)

Entropy Rectifying Guidance for Diffusion and Flow Models
di: Ifriqi, Tariq Berrada, et al.
Pubblicazione: (2025)

DIMCIM: A Quantitative Evaluation Framework for Default-mode Diversity and Generalization in Text-to-Image Generative Models
di: Teotia, Revant, et al.
Pubblicazione: (2025)

PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs
di: Assouel, Rim, et al.
Pubblicazione: (2026)

The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Models
di: Xiaofeng, Zhang, et al.
Pubblicazione: (2025)

Object-centric Binding in Contrastive Language-Image Pretraining
di: Assouel, Rim, et al.
Pubblicazione: (2025)

QGen: On the Ability to Generalize in Quantization Aware Training
di: AskariHemmat, MohammadHossein, et al.
Pubblicazione: (2024)

Boosting Latent Diffusion with Perceptual Objectives
di: Berrada, Tariq, et al.
Pubblicazione: (2024)

Vendi Novelty Scores for Out-of-Distribution Detection
di: Pasarkar, Amey P., et al.
Pubblicazione: (2026)

Controlling Multimodal LLMs via Reward-guided Decoding
di: Mañas, Oscar, et al.
Pubblicazione: (2025)

Why Less is More (Sometimes): A Theory of Data Curation
di: Dohmatob, Elvis, et al.
Pubblicazione: (2025)

What makes a good metric? Evaluating automatic metrics for text-to-image consistency
di: Ross, Candace, et al.
Pubblicazione: (2024)

Augmented Conditioning Is Enough For Effective Training Image Generation
di: Chen, Jiahui, et al.
Pubblicazione: (2025)

Conditional Vendi Score: An Information-Theoretic Approach to Diversity Evaluation of Prompt-based Generative Models
di: Jalali, Mohammad, et al.
Pubblicazione: (2024)

SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance
di: Cong, Peishan, et al.
Pubblicazione: (2025)

On Missing Scores in Evolving Multibiometric Systems
di: Dale, Melissa R, et al.
Pubblicazione: (2024)

How Much Is a Dataset Worth? Scaling Laws, the Vendi Score, and Matrix Spectral Functions
di: Bilmes, Jeff A., et al.
Pubblicazione: (2026)

Guidance-base Diffusion Models for Improving Photoacoustic Image Quality
di: Eguchi, Tatsuhiro, et al.
Pubblicazione: (2025)

Improving Subject-Driven Image Synthesis with Subject-Agnostic Guidance
di: Chan, Kelvin C. K., et al.
Pubblicazione: (2024)

Improving Diffusion Generalization with Weak-to-Strong Segmented Guidance
di: Yuan, Liangyu, et al.
Pubblicazione: (2026)

Conditional Text-to-Image Generation with Reference Guidance
di: Kim, Taewook, et al.
Pubblicazione: (2024)

GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis
di: Sastry, Srikumar, et al.
Pubblicazione: (2024)

Fusion of Deep Learning and GIS for Advanced Remote Sensing Image Analysis
di: Afroosheh, Sajjad, et al.
Pubblicazione: (2024)

Score-Based Matching with Target Guidance for Cryo-EM Denoising
di: Wu, Xiaoqi, et al.
Pubblicazione: (2026)

Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance
di: Choi, June Suk, et al.
Pubblicazione: (2025)

Beyond General Prompts: Automated Prompt Refinement using Contrastive Class Alignment Scores for Disambiguating Objects in Vision-Language Models
di: Choi, Lucas, et al.
Pubblicazione: (2025)

Score-based Conditional Generation with Fewer Labeled Data by Self-calibrating Classifier Guidance
di: Huang, Paul Kuo-Ming, et al.
Pubblicazione: (2023)