MV-FractalDB: Formula-driven Supervised Learning for Multi-view Image Recognition
Ryosuke Yamada, Ryo Takahashi, Ryota Suzuki, Akio Nakamura, Yusuke Yoshiyasu, Ryusuke Sagawa, Hirokatsu Kataoka
Abstract
The paper proposes a method for automatic multi-view dataset construction based on formula-driven supervised learning (FDSL). Although data collection and human annotation of 3D objects are labor-intensive, we automatically generate their training data and labels in the proposed multi-view dataset. To create a large-scale multi-view dataset, we employ fractal geometry, which is considered the background information of many objects in the real world. We project in a circle from the rendered 3D fractal models to construct the Multi-view Fractal DataBase (MV-FractalDB), which is then used to make a pre-trained CNN model. According to the experimental results, the MV-FractalDB pre-trained model surpasses the accuracies with self-supervised methods (e.g., SimCLR and MoCo) and is close to supervised methods (e.g., ImageNet) in terms of performance rates on multi-view image datasets. We demonstrate the potential of FDSL for multi-view image recognition.
BibTeX
@inproceedings{iros2021_mvfractaldbformu,
title = {MV-FractalDB: Formula-driven Supervised Learning for Multi-view Image Recognition},
author = {Ryosuke Yamada and Ryo Takahashi and Ryota Suzuki and Akio Nakamura and Yusuke Yoshiyasu and Ryusuke Sagawa and Hirokatsu Kataoka},
booktitle = {IROS 2021},
year = {2021}
}