Symmetrical irregular local features for fine-grained visual classification

Ming–Hsuan Yang

doi:10.1016/j.neucom.2022.07.056

2022-09-01

PRE

DOI：10.1016/j.neucom.2022.07.056

原文链接

原文求助

摘要

En 中文

Fine-grained visual classification (FGVC) has small inter-class variations and large intra-class variations, therefore, recognizing sub-classes belonging to the same meta-class is a difficult task. Recent studies have primarily addressed this problem by locating the most discriminative image regions, and the extracted image regions have been used to improve the ability to capture subtle differences. Most of these studies used regular anchors to extract local features. However, the local features of the target are mostly irreg-ular geometric shapes. These methods cannot fully extract the features and inevitably include a large amount of irrelevant information, resulting in reduced credibility of the evaluation results. However, the spatial relationship between the features is easily overlooked. This study proposes a novel local fea-ture extraction anchor generator (LFEAG) to simulate the shapes of irregular features. Thus, discrimina-tive features can be fully included in the extracted features. In addition, an effective symmetrized local feature extraction module (SLFEM) based on an attention mechanism is proposed to fully use the spatial relationship between the extracted local features and highlight discriminative features. Experiments on six popular fine-grained benchmark datasets: CUB-200-2011, Stanford Dogs, Food-101, Oxford-IIIT Pets, Aircraft and NA-Birds, are conducted to demonstrate the advantages of our proposed method. (c) 2022 Elsevier B.V. All rights reserved.

Keyword:

Fine-grained image classification

Deep learning

Irregular local features

Discriminative feature

Attention mechanism

Bidirectional long short-term memory