paper-with-me

Papers

Regularized Pooling

2020-05-06 · Takato Otsuzuki, Hideaki Hayashi, Yuchen Zheng, Seiichi Uchida

In convolutional neural networks (CNNs), pooling operations play important roles such as dimensionality reduction and deformation compensation. In general, max pooling, which is the most widely used operation for local pooling, is performed independently for each kernel. However, the deformation may be spatially smooth over the neighboring kernels. This means that max pooling is too flexible to compensate for actual deformations. In other words, its excessive flexibility risks canceling the essential spatial differences between classes. In this paper, we propose regularized pooling, which enables the value selection direction in the pooling operation to be spatially smooth across adjacent kernels so as to compensate only for actual deformations. The results of experiments on handwritten character images and texture images showed that regularized pooling not only improves recognition accuracy but also accelerates the convergence of learning compared with conventional pooling operations.

📄 PDF Abstract BibTeX arXiv:2005.03709

Code (0)

등록된 구현이 없습니다.

Tasks

Dimensionality Reduction

Methods 이 논문이 사용한 방법론

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Similar Papers 제목 키워드 기반

Regularized Optimal Transport Layers for Generalized Global Pooling Operations

2022-12-13 · Hongteng Xu, Minjie Cheng

Global pooling is one of the most significant operations in many machine learning models and tasks, which works for information fusion and structured data (like sets and graphs) representation. However, without solid mat…

Graph Classificationimage-classificationImage Classification

Pooling Regularized Graph Neural Network for fMRI Biomarker Analysis

2020-07-29 · Xiaoxiao Li, Yuan Zhou, Nicha C. Dvornek, Muhan Zhang 외

Understanding how certain brain regions relate to a specific neurological disorder has been an important area of neuroimaging research. A promising approach to identify the salient regions is using Graph Neural Networks …

Graph Neural Network

Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time

2020-06-26 · ICLR 2021 1 · Tolga Ergen, Mert Pilanci

We study training of Convolutional Neural Networks (CNNs) with ReLU activations and introduce exact convex optimization formulations with a polynomial complexity with respect to the number of data samples, the number of …

Unsupervised Feature Learning from Temporal Data

2015-04-09 · Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen 외

Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature lear…

General ClassificationMetric Learning

Unsupervised Learning of Spatiotemporally Coherent Metrics

2014-12-18 · ICCV 2015 12 · Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen 외

Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature lear…

General ClassificationMetric Learning