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!

KLDet: Detecting Tiny Objects in Remote Sensing Images via Kullback–Leibler Divergence

Kullback-Leibler散度 分歧(语言学) 计算机科学 遥感 人工智能 计算机视觉 地质学 语言学 哲学
作者
Zhuangzhuang Zhou,Yingying Zhu
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:62: 1-16 被引量:46
标识
DOI:10.1109/tgrs.2024.3382099
摘要

Remote sensing images (RSIs) frequently contain quite a few tiny objects with a finite number of pixels to study. The limited spatial information poses a challenge for extracting discriminative features for representing the characteristics of tiny objects. Existing solutions mainly focus on aggregating contextual information at different levels, while rarely touching the step that is crucial for model training, i.e., label assignment. Tiny instances occupy fairly small regions of images and have limited overlaps to priors (anchors or dots), which is a dilemma for traditional label assignment strategies. Despite being simple and effective, the mainstream Intersection over Union (IoU)-based label assignment strategy struggles to accurately measure the localization of tiny bounding boxes. In contrast, the Kullback–Leibler divergence (KLD) localization metric accurately reflects minor offsets of tiny bounding boxes. More importantly, KLD is able to measure non-overlapping bounding boxes, providing an advantage in mining more potential positive samples of tiny objects. In this article, from a cost-efficient point of view, we detect tiny objects through KLD in the form of single-stage framework. Specifically, we model the parameterized bounding box as a 2-D Gaussian distribution (Bbox2Gaussian) in order to use KLD as a localization metric. Then, we propose an adaptive online training sample mining (Ali-TSM) strategy based on inter-distribution similarity, which selects high-quality positive samples by considering localization and classification rather than just centroid distance or IoU. Finally, task-level attention (TlA) is introduced to guide the model in freely selecting the appropriate features for the classification or regression task. We conducted extensive experiments on four popular public datasets. Compared to the baseline, KLDet improves performance on Tiny Object Detection in Aerial Images (AI-TOD) and object DetectIon in Optical Remote sensing image (DIOR) by 4.1 AP and 6.7 mAP. On VisDrone and Small Object Detection dAtasets (SODA-D), KLDet exhibits superior performance than baseline. The code is available at https://github.com/TinyOD/mmdet-kldet.
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
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
贺知什么书完成签到,获得积分10
1秒前
Saturday完成签到,获得积分10
2秒前
yx完成签到,获得积分10
2秒前
义气的夏旋完成签到,获得积分10
3秒前
5秒前
ku完成签到 ,获得积分10
8秒前
9秒前
9秒前
Noob_saibot完成签到,获得积分10
11秒前
aa完成签到 ,获得积分10
11秒前
初景发布了新的文献求助10
15秒前
白丶魈白完成签到,获得积分10
17秒前
17秒前
18秒前
kl完成签到,获得积分10
18秒前
SciGPT的应助被花痴的文涛采纳,获得10
19秒前
清新的初雪完成签到 ,获得积分10
21秒前
传奇3的应助被streetlight采纳,获得10
21秒前
木棉发布了新的文献求助10
22秒前
Able发布了新的文献求助10
22秒前
大色国君完成签到 ,获得积分10
24秒前
25秒前
LiuSD完成签到,获得积分10
25秒前
简单的语风完成签到,获得积分10
26秒前
木棉完成签到,获得积分10
30秒前
无花果的应助被白丶魈白采纳,获得10
32秒前
35秒前
35秒前
耳朵在安上完成签到 ,获得积分10
36秒前
38秒前
玛卡巴卡发布了新的文献求助10
39秒前
孤独怀寒完成签到,获得积分10
39秒前
美好的泽洋完成签到 ,获得积分10
40秒前
luo发布了新的文献求助10
42秒前
luo完成签到,获得积分10
47秒前
烟花的应助被null采纳,获得10
49秒前
可可奶黄完成签到,获得积分10
50秒前
李爱国的应助被白丶魈白采纳,获得10
53秒前
NexusExplorer的应助被冰凌采纳,获得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 2000
Handbook of Sport Coaching Research 1000
Orthognathic Surgery - 2 Volume Set 500
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
基于结构调控的功能化水诱导发电材料与器件研究 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 8195028
求助须知:如何正确求助?哪些是违规求助? 9580753
关于积分的说明 21872602
捐赠科研通 7794788
什么是DOI,文献DOI怎么找? 3437855
关于科研通互助平台的介绍 2561176
邀请新用户注册赠送积分活动 2484562