Discretization and Decoupled Knowledge Distillation for Arbitrary Oriented Object Detection

离散化 计算机科学 对象(语法) 蒸馏 面向对象程序设计 域代数上的 人工智能 理论计算机科学 数学 程序设计语言 纯数学 数学分析 色谱法 化学
作者
Chen Cheng,Huiyan Ding,Minglei Duan
出处
期刊:Digital Signal Processing [Elsevier BV]
卷期号:150: 104512-104512
标识
DOI:10.1016/j.dsp.2024.104512
摘要

In recent years, lightweight object detection networks have been increasingly applied to remote sensing platforms due to their fast inference speed and flexible deployment advantages. Knowledge distillation methods have been widely used to reduce the performance gap between large and small models, and many studies have combined knowledge distillation with object detection. However, existing knowledge distillation methods often overlook the transfer of localization knowledge. Therefore, this paper proposes a method called Discretized Position Knowledge Distillation (DPKD) to improve the use of knowledge distillation in object detection. Specifically, the DPKD method incorporates a Discretization Algorithm Module (DAM), which leverages both general probability distribution and cross-Gaussian distribution to transfer high-quality bounding box position and pose information. Additionally, the Position Knowledge Distillation (PKD) method splits the target and non-target bounding boxes to form the distillation loss function, addressing the issue of missing background knowledge transfer during the distillation process. To further enhance the learning of high-quality bounding boxes, a Region Weighting Module (RWM) based on EIoU is introduced in DPKD, assigning weights to the various bounding boxes in the teacher's output. The effectiveness of DPKD in the field of remote sensing image object detection in multi-modal scenarios was verified through multi-modal training on the publicly available DOTA and HRSID datasets.
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
科目三应助Archer采纳,获得10
刚刚
aspen完成签到 ,获得积分10
刚刚
1秒前
彪yu发布了新的文献求助10
2秒前
2秒前
迅速的皮皮虾完成签到,获得积分10
3秒前
zzz完成签到 ,获得积分10
3秒前
爆米花应助甜美的音响采纳,获得10
4秒前
JamesPei应助新羽采纳,获得10
4秒前
乐观羽毛球完成签到,获得积分10
4秒前
4秒前
薄荷加冰发布了新的文献求助10
5秒前
5秒前
诚心的代容完成签到,获得积分10
5秒前
jam发布了新的文献求助10
6秒前
sciscisci完成签到,获得积分10
6秒前
7秒前
李山鬼发布了新的文献求助10
8秒前
要吃烧饼么完成签到,获得积分10
8秒前
8秒前
老迟到的金鱼应助元谷雪采纳,获得10
9秒前
9秒前
刻苦的若南完成签到,获得积分10
9秒前
yy完成签到 ,获得积分10
9秒前
9秒前
传奇3应助彪yu采纳,获得10
9秒前
10秒前
wyl发布了新的文献求助10
10秒前
汉堡包应助樱悼柳雪采纳,获得10
11秒前
11秒前
huayi关注了科研通微信公众号
11秒前
luw2018完成签到,获得积分20
11秒前
量子星尘发布了新的文献求助30
11秒前
lucas完成签到,获得积分10
12秒前
12秒前
12秒前
若雨凌风发布了新的文献求助10
12秒前
13秒前
13秒前
821108pan完成签到 ,获得积分10
14秒前
高分求助中
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
Effective Learning and Mental Wellbeing 300
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 3974463
求助须知:如何正确求助?哪些是违规求助? 3518823
关于积分的说明 11196212
捐赠科研通 3255008
什么是DOI,文献DOI怎么找? 1797655
邀请新用户注册赠送积分活动 877052
科研通“疑难数据库(出版商)”最低求助积分说明 806130