亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

Fast Fine-Grained Image Classification via Weakly Supervised Discriminative Localization

作者
Xiangteng He,Yuxin Peng,Junjie Zhao
出处
期刊:IEEE Transactions on Circuits and Systems for Video Technology [Institute of Electrical and Electronics Engineers]
卷期号:29 (5): 1394-1407 被引量:89
标识
DOI:10.1109/tcsvt.2018.2834480
摘要

Fine-grained image classification is to recognize hundreds of subcategories in each basic-level category. Existing methods employ discriminative localization to find the key distinctions between similar subcategories. However, they generally have two limitations: 1) discriminative localization relies on region proposal methods to hypothesize the locations of discriminative regions, which are time-consuming and the bottleneck of improving classification speed and 2) the training of discriminative localization depends on object or part annotations which are heavily labor-consuming and the obstacle of marching toward practical application. It is highly challenging to address the two limitations simultaneously, while existing methods only focus on one of them. Therefore, we propose a weakly supervised discriminative localization approach (WSDL) for fast fine-grained image classification to address the two limitations at the same time, and its main advantages are: 1) multi-level attention guided localization learning is proposed to localize discriminative regions with different focuses automatically, without using object and part annotations, avoiding the labor consumption. Different level attentions focus on different characteristics of the image, which are complementary and boost classification accuracy and 2) n-pathway end-to-end discriminative localization network is proposed to improve classification speed, which simultaneously localizes multiple different discriminative regions for one image to boost classification accuracy, and shares full-image convolutional features generated by a region proposal network to accelerate the process of generating region proposals as well as reduce the computation of convolutional operation. Both are jointly employed to simultaneously improve classification speed and eliminate dependence on object and part annotations. Comparing with state-of-the-art methods on two widely used fine-grained image classification data sets, our WSDL approach achieves the best accuracy and the efficiency of classification.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
ding的应助被施囧采纳,获得10
1秒前
Lightning123完成签到,获得积分10
2秒前
疯狂的山楂完成签到,获得积分10
3秒前
5秒前
卷卷完成签到 ,获得积分10
7秒前
大模型的应助被困困困困昕采纳,获得10
8秒前
Saturday完成签到,获得积分10
11秒前
施囧发布了新的文献求助10
11秒前
爱笑歌曲完成签到,获得积分10
12秒前
苗条的采梦完成签到,获得积分10
14秒前
CodeCraft的应助被科研通管家采纳,获得10
14秒前
奔跑的应助被科研通管家采纳,获得10
14秒前
null的应助被科研通管家采纳,获得10
15秒前
桐桐的应助被科研通管家采纳,获得10
15秒前
15秒前
17秒前
Yoooo完成签到 ,获得积分10
17秒前
18秒前
gxyqqb完成签到,获得积分20
18秒前
20秒前
李健的粉丝团团长的应助被15采纳,获得10
22秒前
白华苍松发布了新的文献求助10
22秒前
星辰大海的应助被fff采纳,获得10
23秒前
chiaoyin999发布了新的文献求助10
23秒前
Akim的应助被美满惜雪采纳,获得10
26秒前
斯文败类的应助被独特石头采纳,获得10
30秒前
che发布了新的文献求助10
33秒前
35秒前
美满惜雪发布了新的文献求助10
38秒前
冰冰完成签到 ,获得积分10
39秒前
Lee完成签到,获得积分20
40秒前
43秒前
44秒前
秋风的应助被美满惜雪采纳,获得10
45秒前
活力傲柏完成签到,获得积分10
47秒前
48秒前
54秒前
过客完成签到,获得积分10
57秒前
58秒前
Lee发布了新的文献求助10
58秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8184964
求助须知:如何正确求助?哪些是违规求助? 9573917
关于积分的说明 21833687
捐赠科研通 7782425
什么是DOI,文献DOI怎么找? 3434429
关于科研通互助平台的介绍 2558672
邀请新用户注册赠送积分活动 2481161