| LIU Jiatong(刘珈彤),DUAN Yong.[J].高技术通讯(英文),2024,30(3):280~289 |
|
| Few-shot image recognition based on multi-scale features prototypical network |
| |
| DOI：10. 3772 / j. issn. 1006-6748. 2024. 03. 007 |
| 中文关键词: |
| 英文关键词: few-shot learning, multi-scale feature, prototypical network, channel attention,label-smoothing |
| 基金项目: |
| Author Name | Affiliation | | LIU Jiatong(刘珈彤) | (School of Information Science Engineering, Shenyang University of Technology, Shenyang 110870, P. R. China)
(Shenyang Key Laboratory of Advanced Computing and Application Innovation, Shenyang 110870, P. R. China) | | DUAN Yong | |
|
| Hits: 135 |
| Download times: 173 |
| 中文摘要: |
| |
| 英文摘要: |
| In order to improve the model??s capability in expressing features during few-shot learning, a
multi-scale features prototypical network (MS-PN) algorithm is proposed. The metric learning algo-
rithm is employed to extract image features and project them into a feature space, thus evaluating the
similarity between samples based on their relative distances within the metric space. To sufficiently
extract feature information from limited sample data and mitigate the impact of constrained data vol-
ume, a multi-scale feature extraction network is presented to capture data features at various scales
during the process of image feature extraction. Additionally, the position of the prototype is fine-
tuned by assigning weights to data points to mitigate the influence of outliers on the experiment. The
loss function integrates contrastive loss and label-smoothing to bring similar data points closer and
separate dissimilar data points within the metric space. Experimental evaluations are conducted on
small-sample datasets mini-ImageNet and CUB200-2011. The method in this paper can achieve
higher classification accuracy. Specifically, in the 5-way 1-shot experiment, classification accuracy
reaches 50. 13% and 66. 79% respectively on these two datasets. Moreover, in the 5-way 5-shot ex-
periment, accuracy of 66. 79% and 85. 91% are observed, respectively. |
|
View Full Text
View/Add Comment Download reader |
| Close |
|
|
|
