4 papers
Pre-training Vision Transformers with Formula-driven Supervised Learning
Hirokatsu Kataoka, Sora Takashima, Ryo Hayamizu +6
In the present work, we show that the performance of formula-driven supervised learning (FDSL) can match or even exceed that of ImageNet-21k and can approach that of the JFT-300M d…
Industrial Synthetic Segment Pre-training
Shinichi Mae, Ryousuke Yamada, Hirokatsu Kataoka +3
Vision Foundation Models (VFMs) have made remarkable progress and are increasingly being applied to segmentation tasks in real-world industrial settings. However, VFMs pre-trained…
Pre-training with 3D Synthetic Data: Learning 3D Point Cloud Instance Segmentation from 3D Synthetic Scenes
Daichi Otsuka, Shinichi Mae, Ryosuke Yamada +1
In the recent years, the research community has witnessed growing use of 3D point cloud data for the high applicability in various real-world applications. By means of 3D point clo…
Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding
Kohei Torimi, Ryosuke Yamada, Daichi Otsuka +4
Zero-shot recognition models require extensive training data for generalization. However, in zero-shot 3D classification, collecting 3D data and captions is costly and laborintensi…