A multi-layer feature fusion method for few-shot image classification
Αποθηκεύτηκε σε:
| Κύριος συγγραφέας: | |
|---|---|
| Ημερομηνία έκδοσης: | 2023 |
| Άλλοι συγγραφείς: | , |
| Μορφή: | Article |
| Γλώσσα: | eng |
| Πηγή: | Repositório Institucional da UnB |
| Download full: | http://repositorio.unb.br/handle/10482/52466 https://doi.org/10.3390/s23156880 https://orcid.org/0000-0003-4810-5138 https://orcid.org/0000-0001-9284-3299 https://orcid.org/0000-0002-4868-0629 |
Περίληψη: | In image classification, few-shot learning deals with recognizing visual categories from a few tagged examples. The degree of expressiveness of the encoded features in this scenario is a crucial question that needs to be addressed in the models being trained. Recent approaches have achieved encouraging results in improving few-shot models in deep learning, but designing a competitive and simple architecture is challenging, especially considering its requirement in many practical applications. This work proposes an improved few-shot model based on a multi-layer feature fusion (FMLF) method. The presented approach includes extended feature extraction and fusion mechanisms in the Convolutional Neural Network (CNN) backbone, as well as an effective metric to compute the divergences in the end. In order to evaluate the proposed method, a challenging visual classification problem, maize crop insect classification with specific pests and beneficial categories, is addressed, serving both as a test of our model and as a means to propose a novel dataset. Experiments were carried out to compare the results with ResNet50, VGG16, and MobileNetv2, used as feature extraction backbones, and the FMLF method demonstrated higher accuracy with fewer parameters. The proposed FMLF method improved accuracy scores by up to 3.62% in one-shot and 2.82% in fiveshot classification tasks compared to a traditional backbone, which uses only global image features. |
Παρόμοια τεκμήρια: A multi-layer feature fusion method for few-shot image classification
- Insect pest image recognition : a few-shot machine learning approach including maturity stages classification
- Estudo e análise de Redes Neurais Convolucionais Profundas na identificação de doenças em plantas por imagens
- Future-Shot: Few-Shot Learning to tackle new labels on high-dimensional classification problems
- An exploratory assessment of multistream deep neural network fusion : design and applications
- Uma arquitetura de few-shot learning para classificação de insetos na agricultura usando poucas amostras
- Quality assessment of enhanced underwater images with convolutional neural networks