Details

Autor(en) / Beteiligte

• Feng, Wenquan
• Zhang, Boxue
• Lyu, Shuchang
• Zhao, Qi
• Zhang, Xuyun
• Xuyun Zhang

Titel

Multiactivation Pooling Method in Convolutional Neural Networks for Image Recognition

Ist Teil von

• Wireless communications and mobile computing, 2018-01, Vol.2018 (2018), p.1-15

Ort / Verlag

Cairo, Egypt: Hindawi Publishing Corporation

Erscheinungsjahr

2018

Quelle

EZB Electronic Journals Library

Beschreibungen/Notizen

• Convolutional neural networks (CNNs) are becoming more and more popular today. CNNs now have become a popular feature extractor applying to image processing, big data processing, fog computing, etc. CNNs usually consist of several basic units like convolutional unit, pooling unit, activation unit, and so on. In CNNs, conventional pooling methods refer to 2×2 max-pooling and average-pooling, which are applied after the convolutional or ReLU layers. In this paper, we propose a Multiactivation Pooling (MAP) Method to make the CNNs more accurate on classification tasks without increasing depth and trainable parameters. We add more convolutional layers before one pooling layer and expand the pooling region to 4×4, 8×8, 16×16, and even larger. When doing large-scale subsampling, we pick top-k activation, sum up them, and constrain them by a hyperparameter σ. We pick VGG, ALL-CNN, and DenseNets as our baseline models and evaluate our proposed MAP method on benchmark datasets: CIFAR-10, CIFAR-100, SVHN, and ImageNet. The classification results are competitive.