Deep Generalized Max Pooling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2019
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909120452362240 |
|---|---|
| author | Christlein, Vincent Spranger, Lukas Seuret, Mathias Nicolaou, Anguelos Král, Pavel Maier, Andreas |
| author_facet | Christlein, Vincent Spranger, Lukas Seuret, Mathias Nicolaou, Anguelos Král, Pavel Maier, Andreas |
| contents | 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). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1908_05040 |
| institution | arXiv |
| publishDate | 2019 |
| record_format | arxiv |
| spellingShingle | Deep Generalized Max Pooling Christlein, Vincent Spranger, Lukas Seuret, Mathias Nicolaou, Anguelos Král, Pavel Maier, Andreas Computer Vision and Pattern Recognition 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). |
| title | Deep Generalized Max Pooling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/1908.05040 |