Few Shot Object Detection via a Generalized Feature Extraction Net
Abstract
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.
Keywords
Few shot object detection, Fine-tunning, Overfitting, Redundant information
Citation Format:
Dengyong Zhang, Huaijian Pu, Feng Li, R. Simon Sherratt, Se-Jung Lim, "Few Shot Object Detection via a Generalized Feature Extraction Net," Journal of Internet Technology, vol. 24, no. 2 , pp. 305-312, Mar. 2023.
Dengyong Zhang, Huaijian Pu, Feng Li, R. Simon Sherratt, Se-Jung Lim, "Few Shot Object Detection via a Generalized Feature Extraction Net," Journal of Internet Technology, vol. 24, no. 2 , pp. 305-312, Mar. 2023.
Full Text:
PDFRefbacks
- There are currently no refbacks.
Published by Executive Committee, Taiwan Academic Network, Ministry of Education, Taipei, Taiwan, R.O.C
JIT Editorial Office, Office of Library and Information Services, National Dong Hwa University
No. 1, Sec. 2, Da Hsueh Rd., Shoufeng, Hualien 974301, Taiwan, R.O.C.
Tel: +886-3-931-7314 E-mail: jit.editorial@gmail.com