Efficient Two-Step Middle-Level Part Feature Extraction for Fine-Grained Visual Categorization

Hideki NAKAYAMA  Tomoya TSUDA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E99-D   No.6   pp.1626-1634
Publication Date: 2016/06/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2015EDP7358
Type of Manuscript: PAPER
Category: Image Recognition, Computer Vision
Keyword: 
image classification,  fine-grained categorization,  part-based features,  dimensionality reduction,  

Full Text: PDF(899.2KB)>>
Buy this Article




Summary: 
Fine-grained visual categorization (FGVC) has drawn increasing attention as an emerging research field in recent years. In contrast to generic-domain visual recognition, FGVC is characterized by high intra-class and subtle inter-class variations. To distinguish conceptually and visually similar categories, highly discriminative visual features must be extracted. Moreover, FGVC has highly specialized and task-specific nature. It is not always easy to obtain a sufficiently large-scale training dataset. Therefore, the key to success in practical FGVC systems is to efficiently exploit discriminative features from a limited number of training examples. In this paper, we propose an efficient two-step dimensionality compression method to derive compact middle-level part-based features. To do this, we compare both space-first and feature-first convolution schemes and investigate their effectiveness. Our approach is based on simple linear algebra and analytic solutions, and is highly scalable compared with the current one-vs-one or one-vs-all approach, making it possible to quickly train middle-level features from a number of pairwise part regions. We experimentally show the effectiveness of our method using the standard Caltech-Birds and Stanford-Cars datasets.