Imagen de Portada

Discriminative Span as a Predictor of Synthetic Data Utility via Classifier Reconstruction

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Desai, Radhika Amar, Narendra, Modigari
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Exemplar-free Class Incremental Learning via Discriminative and Comparable One-class Classifiers
por: Sun, Wenju, et al.
Publicado: (2022)

Classifier-Free Guidance is a Predictor-Corrector
por: Bradley, Arwen, et al.
Publicado: (2024)

Enhancing the Utility of Privacy-Preserving Cancer Classification using Synthetic Data
por: Osuala, Richard, et al.
Publicado: (2024)

Balancing Fidelity, Utility, and Privacy in Synthetic Cardiac MRI Generation: A Comparative Study
por: Edirisooriya, Madhura, et al.
Publicado: (2026)

LRM-Zero: Training Large Reconstruction Models with Synthesized Data
por: Xie, Desai, et al.
Publicado: (2024)

Adaptive Data Dropout: Towards Self-Regulated Learning in Deep Neural Networks
por: Gahir, Amar, et al.
Publicado: (2026)

Dataset Distillation as Data Compression: A Rate-Utility Perspective
por: Bao, Youneng, et al.
Publicado: (2025)

Deep Image Segmentation via Discriminant Feature Learning
por: Sztamborski, Adam Dawid, et al.
Publicado: (2026)

Synthetically Enhanced: Unveiling Synthetic Data's Potential in Medical Imaging Research
por: Khosravi, Bardia, et al.
Publicado: (2023)

A U-Net and Transformer Pipeline for Multilingual Image Translation
por: Sahay, Siddharth, et al.
Publicado: (2025)

Diffusion Classifier Guidance for Non-robust Classifiers
por: Vaeth, Philipp, et al.
Publicado: (2025)

Exploring the Potential of Synthetic Data to Replace Real Data
por: Lee, Hyungtae, et al.
Publicado: (2024)

On the Equivalency, Substitutability, and Flexibility of Synthetic Data
por: Chang, Che-Jui, et al.
Publicado: (2024)

Synthetic Data for Robust Runway Detection
por: Chigot, Estelle, et al.
Publicado: (2025)

Does the Data Processing Inequality Reflect Practice? On the Utility of Low-Level Tasks
por: Turgeman, Roy, et al.
Publicado: (2025)

Detect Fake with Fake: Leveraging Synthetic Data-driven Representation for Synthetic Image Detection
por: Otake, Hina, et al.
Publicado: (2024)

SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems
por: Ye-Bin, Moon, et al.
Publicado: (2023)

Robust Principal Component Analysis via Discriminant Sample Weight Learning
por: Deng, Yingzhuo, et al.
Publicado: (2024)

Dynamic Classifier-Free Diffusion Guidance via Online Feedback
por: Papalampidi, Pinelopi, et al.
Publicado: (2025)

MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes
por: Wang, Bor-Shiun, et al.
Publicado: (2024)

Neural Field Classifiers via Target Encoding and Classification Loss
por: Yang, Xindi, et al.
Publicado: (2024)

Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
por: Zheng, Kaiwen, et al.
Publicado: (2025)

Do We Need All the Synthetic Data? Targeted Image Augmentation via Diffusion Models
por: Nguyen, Dang, et al.
Publicado: (2025)

UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation
por: Guo, Jiyu, et al.
Publicado: (2025)

AutoDFP: Automatic Data-Free Pruning via Channel Similarity Reconstruction
por: Li, Siqi, et al.
Publicado: (2024)

Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models
por: Shen, Zhirong, et al.
Publicado: (2026)

Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training
por: Dratschuk, Daniel, et al.
Publicado: (2026)

Dealing with Synthetic Data Contamination in Online Continual Learning
por: Wang, Maorong, et al.
Publicado: (2024)

Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning
por: He, Run, et al.
Publicado: (2025)

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

Accurately Classifying Out-Of-Distribution Data in Facial Recognition
por: Barone, Gianluca, et al.
Publicado: (2024)

Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation
por: Liu, Fengbei, et al.
Publicado: (2023)

AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Data
por: Zhao, Zengqun, et al.
Publicado: (2025)

Balancing Two Classifiers via A Simplex ETF Structure for Model Calibration
por: Ni, Jiani, et al.
Publicado: (2025)

SpaNN: Detecting Multiple Adversarial Patches on CNNs by Spanning Saliency Thresholds
por: Victorica, Mauricio Byrd, et al.
Publicado: (2025)

Scalability in Building Component Data Annotation: Enhancing Facade Material Classification with Synthetic Data
por: Harrison, Josie, et al.
Publicado: (2024)

Explainable YOLO-Based Dyslexia Detection in Synthetic Handwriting Data
por: Fink, Nora
Publicado: (2025)

HandCraft: Dynamic Sign Generation for Synthetic Data Augmentation
por: Rios, Gaston Gustavo, et al.
Publicado: (2025)

Position Paper: Building Trust in Synthetic Data for Clinical AI
por: Babu, Krishan Agyakari Raja, et al.
Publicado: (2025)

Provably Improving Generalization of Few-Shot Models with Synthetic Data
por: Nguyen, Lan-Cuong, et al.
Publicado: (2025)