LR-CNN FOR FINE-GRAINED CLASSIFICATION WITH VARYING RESOLUTION

Abstract : In this work, we present an extended study of image representations for fine-grained classification with respect to image resolution. Understudied in literature, this parameter yet presents many practical and theoretical interests, e.g. in embedded systems where restricted computational resources prevent treating high-resolution images. It is thus interesting to figure out which representation provides the best results in this particular context. On this purpose, we evaluate Fisher Vectors and deep representations on two significant fine-grained oriented datasets: FGVC Aircraft and PPMI. We also introduce LR-CNN, a deep structure designed for classification of low-resolution images with strong semantic content. This net provides rich compact features and outperforms both pre-trained deep features and Fisher Vectors.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [26 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01196958
Contributor : Marion Chevalier <>
Submitted on : Thursday, September 10, 2015 - 4:55:50 PM
Last modification on : Thursday, March 21, 2019 - 1:07:43 PM
Document(s) archivé(s) le : Tuesday, December 29, 2015 - 12:17:34 AM

File

Chevalier_ICIP15_LRCNNvaryingr...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01196958, version 1

Citation

Marion Chevalier, Nicolas Thome, Matthieu Cord, Jérôme Fournier, Gilles Henaff, et al.. LR-CNN FOR FINE-GRAINED CLASSIFICATION WITH VARYING RESOLUTION. IEEE International Conference on Image Processing, Sep 2015, Québec city, Canada. ⟨hal-01196958⟩

Share

Metrics

Record views

262

Files downloads

267