Multi-label Image Classification via Coarse-to-Fine Attention
摘要
Great efforts have been made by using deep neural networks to recognize multi-label images.Since multi-label image classification is very complicated,many studies seek to use the attention mechanism as a kind of guidance.Conventional attention-based methods always analyzed images directly and aggressively,which is difficult to well understand complicated scenes.We propose a global/local attention method that can recognize a multi-label image from coarse to fine by mimicking how human-beings observe images.Our global/local attention method first concentrates on the whole image,and then focuses on its local specific objects.We also propose a joint max-margin objective function,which enforces that the minimum score of positive labels should be larger than the maximum score of negative labels horizontally and vertically.This function further improve our multi-label image classification method.We evaluate the effectiveness of our method on two popular multi-label image datasets (i.e.,Pascal VOC and MS-COCO).Our experimental results show that our method outperforms state-of-the-art methods.
Author:
LYU Fan
LI Linyan
Victor S.Sheng
FU Qiming
HU Fuyuan
年,卷(期):
2019, 28(6)
在线出版日期:
2020年11月23日
基金项目:
(No.61876121.No.61472267.No.61728205.No.61502329.No.61672371):This work is supported by the National Natural Science Foundation of China (No.BE2017663):Primary Research & Developement Plan of Jiangsu Province (No.19KJB520054):Natural Science Foundation of the Higher Education Institutions of Jiangsu Province (No.SZS201609.No.SZS201813):and Foundation of Key Laboratory in Science and Technology Development Project of Suzhou,