Hluboký zobecněný max pooling
| Autor: | Anguelos Nicolaou, Lukas Spranger, Pavel Král, Mathias Seuret, Vincent Christlein, Andreas Maier |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer science Computer Vision and Pattern Recognition (cs.CV) Pooling Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Convolutional neural network identifikace pisatele 060104 history hluboké učení 0202 electrical engineering electronic engineering information engineering 0601 history and archaeology pooling Layer (object-oriented design) writer identification business.industry Deep learning Aggregate (data warehouse) analýza dokumentů Contrast (statistics) klasifikace obrazů dokumentů deep learning Pattern recognition 06 humanities and the arts document image classification Identification (information) document analysis 020201 artificial intelligence & image processing Artificial intelligence business |
| Zdroj: | ICDAR |
| Popis: | Global pooling layers are an essential part of Convolutional Neural Networks (CNN). They are used to aggregate activations of spatial locations to produce a fixed-size vector in several state-of-the-art CNNs. Global average pooling or global max pooling are commonly used for converting convolutional features of variable size images to a fix-sized embedding. However, both pooling layer types are computed spatially independent: each individual activation map is pooled and thus activations of different locations are pooled together. In contrast, we propose Deep Generalized Max Pooling that balances the contribution of all activations of a spatially coherent region by re-weighting all descriptors so that the impact of frequent and rare ones is equalized. We show that this layer is superior to both average and max pooling on the classification of Latin medieval manuscripts (CLAMM'16, CLAMM'17), as well as writer identification (Historical-WI'17). ICDAR'19 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|