Hierarchical Feature Attention Learning Network for Detecting Object and Discriminative Parts in Fine-Grained Visual Classification
This paper proposes a novel hierarchical feature attention learning network for improved fine-grained visual classification (FGVC). Existing fine-grained classification methods rely heavily on attention mechanisms to differentiate minute details of similar objects. These mechanisms often assume that...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10854460/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832542563225042944 |
|---|---|
| author | A. Yeong Han Kwang Moo Yi Kyeong Tae Kim Jae Young Choi |
| author_facet | A. Yeong Han Kwang Moo Yi Kyeong Tae Kim Jae Young Choi |
| author_sort | A. Yeong Han |
| collection | DOAJ |
| description | This paper proposes a novel hierarchical feature attention learning network for improved fine-grained visual classification (FGVC). Existing fine-grained classification methods rely heavily on attention mechanisms to differentiate minute details of similar objects. These mechanisms often assume that critical locations have a similar scale and are uniquely localizable, which is not always accurate. For instance, the size of a bird may vary across images, and the color of its beak might only be significant for species identification when its wing and tail colors are specific. This paper addresses this limitation by proposing a so-called hierarchical feature attention learning network, which initially focuses on the target object within the image, followed by multi-headed attention to identify key discriminative locations (patches). Especially, we develop a novel hierarchical attention approach that appropriately reduces misleading attentions by considering the object’s size for capturing correct attention parts. In addition, the proposed multi-headed attention allows for examining more complementary attention parts to identify the most discriminative features. Further, our framework is implemented as an architectural constraint, eliminating the need for object or part-level annotations in a weakly supervised detection manner. We conducted extensive and comparative experiments on three benchmark datasets: NABirds, CUB-200, and Oxford 102 Flower. The results demonstrate that our proposed hierarchical attention approach provides a robust and efficient solution for improved FGVC. Specifically, our method achieved a top-1 accuracy increase of approximately 93.0%, 92.7%, and 99.4% on the CUB-200-2011, NABirds, and Oxford 102 Flower benchmarks, respectively. |
| format | Article |
| id | doaj-art-1a26481913c347d3a065096163443b1a |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-1a26481913c347d3a065096163443b1a2025-02-04T00:00:41ZengIEEEIEEE Access2169-35362025-01-0113195331954410.1109/ACCESS.2025.353444410854460Hierarchical Feature Attention Learning Network for Detecting Object and Discriminative Parts in Fine-Grained Visual ClassificationA. Yeong Han0Kwang Moo Yi1Kyeong Tae Kim2Jae Young Choi3https://orcid.org/0000-0002-3438-8248Department of Computer Engineering, Hankuk University of Foreign Studies, Yongin-si, Republic of KoreaDepartment of Computer Science, The University of British Columbia, Vancouver, BC, CanadaDepartment of Computer Engineering, Hankuk University of Foreign Studies, Yongin-si, Republic of KoreaDepartment of Computer Engineering, Hankuk University of Foreign Studies, Yongin-si, Republic of KoreaThis paper proposes a novel hierarchical feature attention learning network for improved fine-grained visual classification (FGVC). Existing fine-grained classification methods rely heavily on attention mechanisms to differentiate minute details of similar objects. These mechanisms often assume that critical locations have a similar scale and are uniquely localizable, which is not always accurate. For instance, the size of a bird may vary across images, and the color of its beak might only be significant for species identification when its wing and tail colors are specific. This paper addresses this limitation by proposing a so-called hierarchical feature attention learning network, which initially focuses on the target object within the image, followed by multi-headed attention to identify key discriminative locations (patches). Especially, we develop a novel hierarchical attention approach that appropriately reduces misleading attentions by considering the object’s size for capturing correct attention parts. In addition, the proposed multi-headed attention allows for examining more complementary attention parts to identify the most discriminative features. Further, our framework is implemented as an architectural constraint, eliminating the need for object or part-level annotations in a weakly supervised detection manner. We conducted extensive and comparative experiments on three benchmark datasets: NABirds, CUB-200, and Oxford 102 Flower. The results demonstrate that our proposed hierarchical attention approach provides a robust and efficient solution for improved FGVC. Specifically, our method achieved a top-1 accuracy increase of approximately 93.0%, 92.7%, and 99.4% on the CUB-200-2011, NABirds, and Oxford 102 Flower benchmarks, respectively.https://ieeexplore.ieee.org/document/10854460/Fine-grained visual classification (FGVC)hierarchical feature attention learningweakly supervise detectionmulti-head attention |
| spellingShingle | A. Yeong Han Kwang Moo Yi Kyeong Tae Kim Jae Young Choi Hierarchical Feature Attention Learning Network for Detecting Object and Discriminative Parts in Fine-Grained Visual Classification IEEE Access Fine-grained visual classification (FGVC) hierarchical feature attention learning weakly supervise detection multi-head attention |
| title | Hierarchical Feature Attention Learning Network for Detecting Object and Discriminative Parts in Fine-Grained Visual Classification |
| title_full | Hierarchical Feature Attention Learning Network for Detecting Object and Discriminative Parts in Fine-Grained Visual Classification |
| title_fullStr | Hierarchical Feature Attention Learning Network for Detecting Object and Discriminative Parts in Fine-Grained Visual Classification |
| title_full_unstemmed | Hierarchical Feature Attention Learning Network for Detecting Object and Discriminative Parts in Fine-Grained Visual Classification |
| title_short | Hierarchical Feature Attention Learning Network for Detecting Object and Discriminative Parts in Fine-Grained Visual Classification |
| title_sort | hierarchical feature attention learning network for detecting object and discriminative parts in fine grained visual classification |
| topic | Fine-grained visual classification (FGVC) hierarchical feature attention learning weakly supervise detection multi-head attention |
| url | https://ieeexplore.ieee.org/document/10854460/ |
| work_keys_str_mv | AT ayeonghan hierarchicalfeatureattentionlearningnetworkfordetectingobjectanddiscriminativepartsinfinegrainedvisualclassification AT kwangmooyi hierarchicalfeatureattentionlearningnetworkfordetectingobjectanddiscriminativepartsinfinegrainedvisualclassification AT kyeongtaekim hierarchicalfeatureattentionlearningnetworkfordetectingobjectanddiscriminativepartsinfinegrainedvisualclassification AT jaeyoungchoi hierarchicalfeatureattentionlearningnetworkfordetectingobjectanddiscriminativepartsinfinegrainedvisualclassification |