arrow
返回

Weakly-supervised object localization with gradient-pyramid feature

delete2022-05-14
delete2
PRE
AI
Z
Zhongjie Mao
Y
Yipeng Zhou
孙
孙军 (Jun Sun) *
H
Hao Wu
F
Feng Pan
B
Bilal Ahmad
DOI:10.1007/s10489-022-03686-ydelete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
As a basic task of computer vision task, object localization plays an important role in many computer vision based applications. Supervised methods employ manual location labels to learn to localize the objects directly, but incomplete or incorrectly assigned location labels affect localization accuracy, and the cost of manual labelling should also be extremely large. This paper proposes a weakly-supervised localization method based on a multi-scale gradient-pyramid feature, which employs the weighted gradient features on the multiple convolutional layers in order to generate a gradient-pyramid feature for object localization. Pairs of gradients and features from different layers are first extracted to compute the gradient features. Then, during the fusion of the gradient features through a pyramid model, the larger value is selected as the result of the fusion task without using the concatenated method. Finally, the multi-scale gradient-pyramid feature is obtained and used to have a more accurate object localization by using the region scaling operation. Our proposed method can be directly integrated into the pre-trained classification model to perform object localization without additional training. Experimental results on the ILSVRC 2016 dataset and CUB-200-2011 dataset show that the proposed method can achieve better object localization performance.
Keyword:
Weakly-supervised object localization
Multi-scale gradients and features
Pyramid model

期刊

Applied Intelligence 封面图
Applied Intelligence
IF:
3.5
论文数:
7.6K
被引数:
1.7W

机构

J
Jiangnan University
学者数:
3.9W
论文数: 2.7W
被引数: 4.7W
引用论文

引用论文

In-Hand Object Localization Using a Novel High-Resolution Visuotactile Sensor
err2022-06-01
err46
PREAI
errCui, Shaowei; Wang, Rui; Hu, Jingyi; Wei, Junhang; Wang, Shuo; Lou, Zheng
err分享
err收藏
FTIR and Raman analysis of PbBr2-CdO-Bi2O3-B2O3 glasses
err2023-01-01
err0
PREAI
errG. Nagaraju; K. Chandra Sekhar; Md. Shareefuddin; D. Karuna Sagar
err分享
err收藏
Top-Down Neural Attention by Excitation Backprop自上而下的神经注意力通过激励背prop
err2017-12-23
err413
PREAI
errZhang, Jianming; Bargal, Sarah Adel; Lin, Zhe; Brandt, Jonathan; Shen, Xiaohui; Sclaroff, Stan
err分享
err收藏
学者 查看更多内容