Dual-stream Reconstruction Network for Multi-label and Few-shot Learning
The multi-label image classification problem is one of the most important problems in the field of computer vision,which needs to predict and output all the labels in an image.However,the number of labels to be classified in an image is often more than one,and the changeable size,posture,and positio...
Main Author: | FANG Zhong-li, WANG Zhe, CHI Zi-qiu |
---|---|
Format: | Article |
Language: | zho |
Published: |
Editorial office of Computer Science
2022-01-01
|
Series: | Jisuanji kexue |
Subjects: | |
Online Access: | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-1-212.pdf |
Similar Items
-
Boosting Few-Shot Hyperspectral Image Classification Using Pseudo-Label Learning
by: Chen Ding, et al.
Published: (2021-09-01) -
FRDet: Few‐shot object detection via feature reconstruction
by: Zhihao Chen, et al.
Published: (2023-10-01) -
Few-Shot Learning Based on Double Pooling Squeeze and Excitation Attention
by: Qiuyu Xu, et al.
Published: (2022-12-01) -
HCPNet: Learning discriminative prototypes for few-shot remote sensing image scene classification
by: Junjie Zhu, et al.
Published: (2023-09-01) -
Multi-Scale Decision Network With Feature Fusion and Weighting for Few-Shot Learning
by: Xiaoru Wang, et al.
Published: (2020-01-01)