LR-CNN FOR FINE-GRAINED CLASSIFICATION WITH VARYING RESOLUTION - Archive ouverte HAL Access content directly
Conference Papers Year :

LR-CNN FOR FINE-GRAINED CLASSIFICATION WITH VARYING RESOLUTION

(1, 2) , (2) , (2) , (1) , (1) , (1)
1
2

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.
Fichier principal
Vignette du fichier
Chevalier_ICIP15_LRCNNvaryingresolution.pdf (386.29 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01196958 , version 1 (10-09-2015)

Identifiers

  • HAL Id : hal-01196958 , version 1

Cite

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⟩
234 View
349 Download

Share

Gmail Facebook Twitter LinkedIn More