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

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

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 intraclass and subtle inter-class variations. To distinguish conceptually and visually similar categories, highly discriminative visual features must be extracted. Moreover, FGVC has highly special...

Co-Segmentation for Fine Grained Visual Categorization

In this extended abstract we review our works [1, 2] on fine-grained visual classification (FGVC) and present the most recent results of our classification pipeline. In particular, we focus on the importance of the foreground segmentation, and show that accurate segmentation of training images is highly beneficial for the accuracy of classification at test time. We demonstrate the merit of rela...

Visual Representations for Fine-grained Categorization

Visual Representations for Fine-grained Categorization

Advances in fine-grained visual categorization

Fine-grained categorization via CNN-based automatic extraction and integration of object-level and part-level features

Fine-grained categorization can benefit from part-based features which reveal subtle visual differences between object categories. Handcrafted features have been widely used for part detection and classification. Although a recent trend seeks to learn such features automatically using powerful deep learning models such as convolutional neural networks (CNN), their training and possibly also tes...