Search Results for author: Jiaxin Ma

Found 6 papers, 2 papers with code

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

no code implementations4 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 implementation19 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 implementation4 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 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.

Adaptive Distillation for Decentralized Learning from Heterogeneous Clients

no code implementations18 Aug 2020 Jiaxin Ma, Ryo Yonetani, Zahid Iqbal

This paper addresses the problem of decentralized learning to achieve a high-performance global model by asking a group of clients to share local models pre-trained with their own data resources.

Federated Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.