篇名 |
Few Shot Object Detection via a Generalized Feature Extraction Net
|
---|---|
並列篇名 | Few Shot Object Detection via a Generalized Feature Extraction Net |
作者 | Dengyong Zhang、Huaijian Pu、Feng Li、R. Simon Sherratt、Se-Jung Lim |
英文摘要 | It is a new problem for deep learning to train a model on a small number of known targets to detect this object. Many recent studies are based on fine-tuning methods to solve. However, there is a lot of redundant information in the model during feature extraction, which will aggravate the difficulty of fine-tuning the model. Moreover, the neural network using the cross-entropy loss function classifier trained in few shots is prone to overfitting. We use the RS structure to reduce the number of channels in the model to reduce the repeated features in feature extraction. In addition, we use the Pearson distance function to calculate the classification loss of the model, to use the nonparametric method to reduce the number of parameters and prevent overfitting. Experimental results show that our method is better than the previous methods on Pascal VOC and FSOD datasets.
|
起訖頁 | 305-312 |
關鍵詞 | Few shot object detection、Fine-tunning、Overfitting、Redundant information |
刊名 | 網際網路技術學刊 |
期數 | 202303 (24:2期) |
出版單位 | 台灣學術網路管理委員會 |
DOI |
|
QR Code | |
該期刊 上一篇
| Discovering and Mapping Subnet Level Topology |
該期刊 下一篇
| An Enhanced Explicit Port Forwarding Solution for Improving Video Delivery over Software-Defined Networks |