1 citations · 2 across the 15 of their papers we have counts for
16 papers
Improving Imitation Learning Efficiency for Manipulation through Geometric Prior Pretraining
Shogo Iwakata, Tomohiro Motoda, Ryosuke Yamada +8
Applying an imitation learning policy to a new manipulation task usually requires collecting new demonstrations and retraining the model, which makes sample efficiency a practical…
FDIF: Formula-Driven supervised Learning with Implicit Functions for 3D Medical Image Segmentation
Yukinori Yamamoto, Kazuya Nishimura, Tsukasa Fukusato +3
Deep learning-based 3D medical image segmentation methods relies on large-scale labeled datasets, yet acquiring such data is difficult due to privacy constraints and the high cost…
3D sans 3D Scans: Scalable Pre-training from Video-Generated Point Clouds
Ryousuke Yamada, Kohsuke Ide, Yoshihiro Fukuhara +4
Despite recent progress in 3D self-supervised learning, collecting large-scale 3D scene scans remains expensive and labor-intensive. In this work, we investigate whether 3D represe…
S3OD: Towards Generalizable Salient Object Detection with Synthetic Data
Orest Kupyn, Hirokatsu Kataoka, Christian Rupprecht
Salient object detection exemplifies data-bounded tasks where expensive pixel-precise annotations force separate model training for related subtasks like DIS and HR-SOD. We present…
AgroBench: Vision-Language Model Benchmark in Agriculture
Risa Shinoda, Nakamasa Inoue, Hirokatsu Kataoka +2
Precise automated understanding of agricultural tasks such as disease identification is essential for sustainable crop production. Recent advances in vision-language models (VLMs)…
AnimalClue: Recognizing Animals by their Traces
Risa Shinoda, Nakamasa Inoue, Iro Laina +2
Wildlife observation plays an important role in biodiversity conservation, necessitating robust methodologies for monitoring wildlife populations and interspecies interactions. Rec…
Industrial Synthetic Segment Pre-training
Shinichi Mae, Hirokatsu Kataoka, Ryousuke Yamada +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…
On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process
Shun Iwase, Shuya Takahashi, Nakamasa Inoue +3
The double descent phenomenon, which deviates from the traditional bias-variance trade-off theory, attracts considerable research attention; however, the mechanism of its occurrenc…
Can masking background and object reduce static bias for zero-shot action recognition?
Takumi Fukuzawa, Kensho Hara, Hirokatsu Kataoka +1
In this paper, we address the issue of static bias in zero-shot action recognition. Action recognition models need to represent the action itself, not the appearance. However, some…
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…
Constant Rate Scheduling: A General Framework for Optimizing Diffusion Noise Schedule via Distributional Change
Shuntaro Okada, Kenji Doi, Ryota Yoshihashi +2
We propose a general framework for optimizing noise schedules in diffusion models, applicable to both training and sampling. Our method enforces a constant rate of change in the pr…
Formula-Supervised Visual-Geometric Pre-training
Ryosuke Yamada, Kensho Hara, Hirokatsu Kataoka +4
Throughout the history of computer vision, while research has explored the integration of images (visual) and point clouds (geometric), many advancements in image and 3D object rec…
Rethinking Image Super-Resolution from Training Data Perspectives
Go Ohtani, Ryu Tadokoro, Ryosuke Yamada +7
In this work, we investigate the understudied effect of the training data used for image super-resolution (SR). Most commonly, novel SR methods are developed and benchmarked on com…
Scaling Backwards: Minimal Synthetic Pre-training?
Ryo Nakamura, Ryu Tadokoro, Ryosuke Yamada +6
Pre-training and transfer learning are an important building block of current computer vision systems. While pre-training is usually performed on large real-world image datasets, i…
Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation
Ryota Yoshihashi, Yuya Otsuka, Kenji Doi +2
The advance of generative models for images has inspired various training techniques for image recognition utilizing synthetic images. In semantic segmentation, one promising appro…