Universal Fine-grained Visual Categorization by Concept Guided Learning

分类 计算机科学 判别式 代表(政治) 人工智能 可视化 自然语言处理 对象(语法) 情报检索 政治 政治学 法学
作者
Qi Bi,Beichen Zhou,Wei Ji,Gui-Song Xia
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:34: 394-409 被引量:1
标识
DOI:10.1109/tip.2024.3523802
摘要

Existing fine-grained visual categorization (FGVC) methods assume that the fine-grained semantics rest in the informative parts of an image. This assumption works well on favorable front-view object-centric images, but can face great challenges in many real-world scenarios, such as scene-centric images ( e.g. , street view) and adverse viewpoint ( e.g. , object reidentification, remote sensing). In such scenarios, the mis-/over-feature activation is likely to confuse the part selection and degrade the fine-grained representation. In this paper, we are motivated to design a universal FGVC framework for real-world scenarios. More precisely, we propose a concept guided learning (CGL), which models concepts of a certain fine-grained category as a combination of inherited concepts from its subordinate coarse-grained category and discriminative concepts from its own. The discriminative concepts is utilized to guide the fine-grained representation learning. Specifically, three key steps are designed, namely, concept mining, concept fusion, and concept constraint. On the other hand, to bridge the FGVC dataset gap under scene-centric and adverse viewpoint scenarios, a Fine-grained Land-cover Categorization Dataset (FGLCD) with 59,994 fine-grained samples is proposed. Extensive experiments show the proposed CGL: 1) has a competitive performance on conventional FGVC; 2) achieves state-of-the-art performance on fine-grained aerial scenes & scene-centric street scenes; 3) good generalization on object re-identification and fine-grained aerial object detection. The dataset and source code will be available at https://github.com/BiQiWHU/CGL.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
1秒前
moji发布了新的文献求助10
2秒前
Imp完成签到,获得积分10
4秒前
4秒前
5秒前
量子星尘发布了新的文献求助10
5秒前
6秒前
33发布了新的文献求助30
6秒前
彦卿完成签到 ,获得积分10
7秒前
思源应助赵清持采纳,获得10
8秒前
张雯思发布了新的文献求助10
9秒前
Orange应助Shrine采纳,获得10
10秒前
11秒前
卡卡罗特发布了新的文献求助10
11秒前
cdytjt完成签到,获得积分10
13秒前
16秒前
ding应助小田心采纳,获得10
16秒前
16秒前
16秒前
17秒前
17秒前
wwl发布了新的文献求助10
18秒前
鹏程万里完成签到,获得积分10
19秒前
星辰大海应助li采纳,获得10
20秒前
chasikan发布了新的文献求助30
21秒前
cxy发布了新的文献求助10
22秒前
幸福大白发布了新的文献求助10
23秒前
大个应助贾克斯采纳,获得10
25秒前
过时的画板完成签到,获得积分10
25秒前
大气小蘑菇完成签到,获得积分10
28秒前
29秒前
小田心发布了新的文献求助10
35秒前
千跃举报求助违规成功
35秒前
whatever举报求助违规成功
35秒前
wdy111举报求助违规成功
35秒前
35秒前
tongluobing完成签到,获得积分10
36秒前
我是老大应助深情的雁露采纳,获得10
37秒前
38秒前
Singularity应助爱笑晓曼采纳,获得20
38秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989406
求助须知:如何正确求助?哪些是违规求助? 3531522
关于积分的说明 11254187
捐赠科研通 3270174
什么是DOI,文献DOI怎么找? 1804901
邀请新用户注册赠送积分活动 882105
科研通“疑难数据库(出版商)”最低求助积分说明 809174