Guardado en:
Detalles Bibliográficos
Autores principales: Bruintjes, Robert-Jan, Lengyel, Attila, Kayhan, Osman Semih, Zambrano, Davide, Tömen, Nergis, Jamali-Rad, Hadi, van Gemert, Jan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2506.08612
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908402101256192
author Bruintjes, Robert-Jan
Lengyel, Attila
Kayhan, Osman Semih
Zambrano, Davide
Tömen, Nergis
Jamali-Rad, Hadi
van Gemert, Jan
author_facet Bruintjes, Robert-Jan
Lengyel, Attila
Kayhan, Osman Semih
Zambrano, Davide
Tömen, Nergis
Jamali-Rad, Hadi
van Gemert, Jan
contents Deep Learning requires large amounts of data to train models that work well. In data-deficient settings, performance can be degraded. We investigate which Deep Learning methods benefit training models in a data-deficient setting, by organizing the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" workshop series, featuring four editions of data-impaired challenges. These challenges address the problem of training deep learning models for computer vision tasks with limited data. Participants are limited to training models from scratch using a low number of training samples and are not allowed to use any form of transfer learning. We aim to stimulate the development of novel approaches that incorporate prior knowledge to improve the data efficiency of deep learning models. Successful challenge entries make use of large model ensembles that mix Transformers and CNNs, as well as heavy data augmentation. Novel prior knowledge-based methods contribute to success in some entries.
format Preprint
id arxiv_https___arxiv_org_abs_2506_08612
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Data-Efficient Challenges in Visual Inductive Priors: A Retrospective
Bruintjes, Robert-Jan
Lengyel, Attila
Kayhan, Osman Semih
Zambrano, Davide
Tömen, Nergis
Jamali-Rad, Hadi
van Gemert, Jan
Computer Vision and Pattern Recognition
Deep Learning requires large amounts of data to train models that work well. In data-deficient settings, performance can be degraded. We investigate which Deep Learning methods benefit training models in a data-deficient setting, by organizing the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" workshop series, featuring four editions of data-impaired challenges. These challenges address the problem of training deep learning models for computer vision tasks with limited data. Participants are limited to training models from scratch using a low number of training samples and are not allowed to use any form of transfer learning. We aim to stimulate the development of novel approaches that incorporate prior knowledge to improve the data efficiency of deep learning models. Successful challenge entries make use of large model ensembles that mix Transformers and CNNs, as well as heavy data augmentation. Novel prior knowledge-based methods contribute to success in some entries.
title Data-Efficient Challenges in Visual Inductive Priors: A Retrospective
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.08612