Analysis of convolutional neural network image classifiers in a hierarchical max-pooling model with additional local pooling
This work addresses image classification for computer vision applications, but it appears incremental as it builds on existing hierarchical and pooling models without claiming major breakthroughs.
The paper tackles image classification by introducing a hierarchical max-pooling model with additional local pooling to handle variable relative distances between image parts, and it compares various convolutional neural network classifiers in terms of convergence rates, analyzing performance on simulated and real data.
Image classification is considered, and a hierarchical max-pooling model with additional local pooling is introduced. Here the additional local pooling enables the hierachical model to combine parts of the image which have a variable relative distance towards each other. Various convolutional neural network image classifiers are introduced and compared in view of their rate of convergence. The finite sample size performance of the estimates is analyzed by applying them to simulated and real data.