Few-Shot Fine-Grained Classification With Rotation-Invariant Feature Map Complementary Reconstruction Network

Yangfan Li, Liang Chen*, Wei Li, Nan Wang

*此作品的通讯作者

科研成果: 期刊稿件文章同行评审

6 引用 (Scopus)

摘要

Fine-grained classification is of significant importance in the field of remote sensing. However, obtaining valuable and rare target images is often a challenging task, giving rise to the few-shot fine-grained classification problem. In response to this challenge, various meta-learning approaches have been introduced, with the feature map reconstruction network (FRN) emerging as a prominent method. Targets in remote-sensing images exhibit arbitrary orientation, substantial interclass similarity, and intraclass diversity. Nevertheless, the conventional FRN exhibits subpar performance due to its inability to handle rotational variations. Moreover, it only reconstructs features from a single-channel dimension of support features, neglecting the interplay between different dimensions and resulting in inaccurate reconstruction errors. To overcome the challenges of imprecise rotational variation features for reconstruction and inaccurate reconstruction errors, we propose a rotation-invariant feature map complementary reconstruction network (RIFCRN). The RIFCRN involves several key innovations. First, we introduce a novel rotation-invariant module (RIM) based on active rotating filters (ARFs) and oriented response pooling, enabling the extraction of rotation-invariant features for reconstruction. This modification enhances the suitability of the FRN for the few-shot fine-grained classification problem. Second, we put forward a novel feature map complementary reconstruction (CPR) method that calculates the CPR errors (CREs) which effectively captures relationships among different feature map dimensions and results in more accurate reconstruction errors. Finally, extensive experiments have been conducted to validate the effectiveness of the proposed RIFCRN in addressing the few-shot fine-grained classification problem. The code will be available at https://github.com/liyangfan0/RIFCRN.

源语言英语
文章编号5608312
页(从-至)1-12
页数12
期刊IEEE Transactions on Geoscience and Remote Sensing
62
DOI
出版状态已出版 - 2024

指纹

探究 'Few-Shot Fine-Grained Classification With Rotation-Invariant Feature Map Complementary Reconstruction Network' 的科研主题。它们共同构成独一无二的指纹。

引用此

Li, Y., Chen, L., Li, W., & Wang, N. (2024). Few-Shot Fine-Grained Classification With Rotation-Invariant Feature Map Complementary Reconstruction Network. IEEE Transactions on Geoscience and Remote Sensing, 62, 1-12. 文章 5608312. https://doi.org/10.1109/TGRS.2024.3361501