Feature fusion network based on few-shot fine-grained classification
The objective of few-shot fine-grained learning is to identify subclasses within a primary class using a limited number of labeled samples. However, many current methodologies rely on the metric of singular feature, which is either global or local. In fine-grained image classification tasks, where t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-11-01
|
| Series: | Frontiers in Neurorobotics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnbot.2023.1301192/full |
| _version_ | 1827763943856144384 |
|---|---|
| author | Yajie Yang Yuxuan Feng Li Zhu Haitao Fu Xin Pan Chenlei Jin |
| author_facet | Yajie Yang Yuxuan Feng Li Zhu Haitao Fu Xin Pan Chenlei Jin |
| author_sort | Yajie Yang |
| collection | DOAJ |
| description | The objective of few-shot fine-grained learning is to identify subclasses within a primary class using a limited number of labeled samples. However, many current methodologies rely on the metric of singular feature, which is either global or local. In fine-grained image classification tasks, where the inter-class distance is small and the intra-class distance is big, relying on a singular similarity measurement can lead to the omission of either inter-class or intra-class information. We delve into inter-class information through global measures and tap into intra-class information via local measures. In this study, we introduce the Feature Fusion Similarity Network (FFSNet). This model employs global measures to accentuate the differences between classes, while utilizing local measures to consolidate intra-class data. Such an approach enables the model to learn features characterized by enlarge inter-class distances and reduce intra-class distances, even with a limited dataset of fine-grained images. Consequently, this greatly enhances the model's generalization capabilities. Our experimental results demonstrated that the proposed paradigm stands its ground against state-of-the-art models across multiple established fine-grained image benchmark datasets. |
| first_indexed | 2024-03-11T10:57:51Z |
| format | Article |
| id | doaj.art-0a1c2175127946f5aa7406cfb9910151 |
| institution | Directory Open Access Journal |
| issn | 1662-5218 |
| language | English |
| last_indexed | 2024-03-11T10:57:51Z |
| publishDate | 2023-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurorobotics |
| spelling | doaj.art-0a1c2175127946f5aa7406cfb99101512023-11-13T03:15:34ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182023-11-011710.3389/fnbot.2023.13011921301192Feature fusion network based on few-shot fine-grained classificationYajie YangYuxuan FengLi ZhuHaitao FuXin PanChenlei JinThe objective of few-shot fine-grained learning is to identify subclasses within a primary class using a limited number of labeled samples. However, many current methodologies rely on the metric of singular feature, which is either global or local. In fine-grained image classification tasks, where the inter-class distance is small and the intra-class distance is big, relying on a singular similarity measurement can lead to the omission of either inter-class or intra-class information. We delve into inter-class information through global measures and tap into intra-class information via local measures. In this study, we introduce the Feature Fusion Similarity Network (FFSNet). This model employs global measures to accentuate the differences between classes, while utilizing local measures to consolidate intra-class data. Such an approach enables the model to learn features characterized by enlarge inter-class distances and reduce intra-class distances, even with a limited dataset of fine-grained images. Consequently, this greatly enhances the model's generalization capabilities. Our experimental results demonstrated that the proposed paradigm stands its ground against state-of-the-art models across multiple established fine-grained image benchmark datasets.https://www.frontiersin.org/articles/10.3389/fnbot.2023.1301192/fullfew-shot classificationfine-grained classificationsimilarity measurementinter-class distinctivenessintra-class compactness |
| spellingShingle | Yajie Yang Yuxuan Feng Li Zhu Haitao Fu Xin Pan Chenlei Jin Feature fusion network based on few-shot fine-grained classification Frontiers in Neurorobotics few-shot classification fine-grained classification similarity measurement inter-class distinctiveness intra-class compactness |
| title | Feature fusion network based on few-shot fine-grained classification |
| title_full | Feature fusion network based on few-shot fine-grained classification |
| title_fullStr | Feature fusion network based on few-shot fine-grained classification |
| title_full_unstemmed | Feature fusion network based on few-shot fine-grained classification |
| title_short | Feature fusion network based on few-shot fine-grained classification |
| title_sort | feature fusion network based on few shot fine grained classification |
| topic | few-shot classification fine-grained classification similarity measurement inter-class distinctiveness intra-class compactness |
| url | https://www.frontiersin.org/articles/10.3389/fnbot.2023.1301192/full |
| work_keys_str_mv | AT yajieyang featurefusionnetworkbasedonfewshotfinegrainedclassification AT yuxuanfeng featurefusionnetworkbasedonfewshotfinegrainedclassification AT lizhu featurefusionnetworkbasedonfewshotfinegrainedclassification AT haitaofu featurefusionnetworkbasedonfewshotfinegrainedclassification AT xinpan featurefusionnetworkbasedonfewshotfinegrainedclassification AT chenleijin featurefusionnetworkbasedonfewshotfinegrainedclassification |