Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Crulis, Ben, Serres, Barthelemy, De Runz, Cyril, Venturini, Gilles
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2410.16028
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916447911936000
author Crulis, Ben
Serres, Barthelemy
De Runz, Cyril
Venturini, Gilles
author_facet Crulis, Ben
Serres, Barthelemy
De Runz, Cyril
Venturini, Gilles
contents Current large open vision models could be useful for one and few-shot object recognition. Nevertheless, gradient-based re-training solutions are costly. On the other hand, open-vocabulary object detection models bring closer visual and textual concepts in the same latent space, allowing zero-shot detection via prompting at small computational cost. We propose a lightweight method to turn the latter into a one-shot or few-shot object recognition models without requiring textual descriptions. Our experiments on the TEgO dataset using the YOLO-World model as a base show that performance increases with the model size, the number of examples and the use of image augmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16028
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Few-shot target-driven instance detection based on open-vocabulary object detection models
Crulis, Ben
Serres, Barthelemy
De Runz, Cyril
Venturini, Gilles
Computer Vision and Pattern Recognition
Current large open vision models could be useful for one and few-shot object recognition. Nevertheless, gradient-based re-training solutions are costly. On the other hand, open-vocabulary object detection models bring closer visual and textual concepts in the same latent space, allowing zero-shot detection via prompting at small computational cost. We propose a lightweight method to turn the latter into a one-shot or few-shot object recognition models without requiring textual descriptions. Our experiments on the TEgO dataset using the YOLO-World model as a base show that performance increases with the model size, the number of examples and the use of image augmentation.
title Few-shot target-driven instance detection based on open-vocabulary object detection models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.16028