TNF: Tri-branch Neural Fusion for Multimodal Medical Data Classification

no code implementations • 4 Mar 2024 • Tong Zheng, Shusaku Sone, Yoshitaka Ushiku, Yuki Oba, Jiaxin Ma

This paper presents a Tri-branch Neural Fusion (TNF) approach designed for classifying multimodal medical images and tabular data.

WeaveNet for Approximating Two-sided Matching Problems

1 code implementation • 19 Oct 2023 • Shusaku Sone, Jiaxin Ma, Atsushi Hashimoto, Naoya Chiba, Yoshitaka Ushiku

Matching, a task to optimally assign limited resources under constraints, is a fundamental technology for society.

Efficient Neural Network

3D Point Cloud Registration with Learning-based Matching Algorithm

1 code implementation • 4 Feb 2022 • rintaro yanagi, Atsushi Hashimoto, Shusaku Sone, Naoya Chiba, Jiaxin Ma, Yoshitaka Ushiku

Instead of only optimizing the feature extractor for a matching algorithm, we propose a learning-based matching module optimized to the jointly-trained feature extractor.

Point Cloud Registration

WeaveNet: A Differentiable Solver for Non-linear Assignment Problems

no code implementations • 29 Sep 2021 • Shusaku Sone, Atsushi Hashimoto, Jiaxin Ma, rintaro yanagi, Naoya Chiba, Yoshitaka Ushiku

Assignment, a task to match a limited number of elements, is a fundamental problem in informatics.

3D Point Cloud Matching Combinatorial Optimization

WeaveNet for Approximating Assignment Problems

no code implementations • NeurIPS 2021 • Shusaku Sone, Jiaxin Ma, Atsushi Hashimoto, Naoya Chiba, Yoshitaka Ushiku

Assignment, a task to match a limited number of elements, is a fundamental problem in informatics.