Development of learning subspace-based methods for pattern recognition

基于学习子空间的模式识别方法的开发

基本信息

批准号：
22K17960
负责人：
SALESDESOUZA LINCON
金额：
$ 3万
依托单位：
National Institute of Advanced Industrial Science and Technology
依托单位国家：
日本
项目类别：
Grant-in-Aid for Early-Career Scientists
财政年份：
2022
资助国家：
日本
起止时间：
2022-04-01 至 2026-03-31
项目状态：
未结题

来源：
https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-22K17960/
关键词：
Subspace learning Deep neural networks Manifold optimization Subspace methods Pattern recognition

项目摘要

In fiscal year 2022, we worked to address the problem that traditional deep neural network frameworks process image sets independently, without considering the underlying feature distribution and the variance of the images in the set. To overcome this limitation, we devised a new subspace learning method called Grassmannian learning mutual subspace method (G-LMSM), which is an NN layer that can be integrated into deep neural networks.G-LMSM maps the image set into a low-dimensional input subspace representation, which is then matched with dictionary subspaces using a similarity metric of their canonical angles, an interpretable and computationally efficient metric. The key idea of G-LMSM is to learn dictionary subspaces as points on the Grassmann manifold, which is a smooth, non-linear manifold that captures the geometric structure of subspaces. This learning is optimized with Riemannian stochastic gradient descent, which is stable, efficient, and theoretically well-grounded.The proposed method was evaluated on three different tasks: hand shape recognition, face identification, and facial emotion recognition. Our experimental results showed that G-LMSM outperformed state-of-the-art methods on all three tasks, demonstrating its potential to improve the performance of deep frameworks for object recognition from image sets.

在2022财年，我们致力于解决传统深度神经网络框架独立处理图像集，而不考虑底层特征分布和集合中图像的方差的问题。为了克服这个限制，我们设计了一种新的子空间学习方法，称为格拉斯曼学习互子空间方法（G-LMSM），它是一个可以集成到深度神经网络中的NN层。G-LMSM将图像集映射到低维输入子空间表示，然后使用其规范角度的相似性度量（一种可解释且计算高效的度量）与字典子空间进行匹配。 G-LMSM 的关键思想是将字典子空间学习为格拉斯曼流形上的点，格拉斯曼流形是一个平滑的非线性流形，可捕获子空间的几何结构。该学习采用黎曼随机梯度下降进行优化，稳定、高效且理论基础良好。所提出的方法在三个不同的任务上进行了评估：手形识别、人脸识别和面部情绪识别。我们的实验结果表明，G-LMSM 在所有三个任务上都优于最先进的方法，展示了其提高图像集对象识别深度框架性能的潜力。

项目成果

期刊论文数量（4）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Analysis of Temporal Tensor Datasets on Product Grassmann Manifold

DOI：
10.1109/cvprw56347.2022.00534
发表时间：
2022-06
期刊：
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
影响因子：
0
作者：
Bojan Batalo;L. S. Souza;B. Gatto;Naoya Sogi;K. Fukui
通讯作者：
Bojan Batalo;L. S. Souza;B. Gatto;Naoya Sogi;K. Fukui

Grassmannian learning mutual subspace method for image set recognition