Compact bilinear pooling via kernelized random projection for fine-grained image categorization on low computational power devices
[EN]Bilinear pooling is one of the most popular and effective methods for fine-grained image recognition. However, a major drawback of Bilinear pooling is the dimensionality of the resulting descriptors, which typically consist of several hundred thousand features. Even when generating the descripto...
| Autores: | , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2020 |
| País: | España |
| Institución: | Universidad de Salamanca (USAL) |
| Repositorio: | GREDOS. Repositorio Institucional de la Universidad de Salamanca |
| OAI Identifier: | oai:gredos.usal.es:10366/145808 |
| Acceso en línea: | http://hdl.handle.net/10366/145808 |
| Access Level: | acceso abierto |
| Palabra clave: | Bilinear pooling Deep learning Random projection Polynomial kernel 1203.17 Informática 1203.04 Inteligencia Artificial |
| Sumario: | [EN]Bilinear pooling is one of the most popular and effective methods for fine-grained image recognition. However, a major drawback of Bilinear pooling is the dimensionality of the resulting descriptors, which typically consist of several hundred thousand features. Even when generating the descriptor is tractable, its dimension makes any subsequent operations impractical and often results in huge computational and storage costs. We introduce a novel method to efficiently reduce the dimension of bilinear pooling descriptors by performing a Random Projection. Conveniently, this is achieved without ever computing the high-dimensional descriptor explicitly. Our experimental results show that our method outperforms existing compact bilinear pooling algorithms in most cases, while running faster on low computational power devices, where efficient extensions of bilinear pooling are most useful. |
|---|