LDConv: Linear deformable convolution for improving convolutional neural networks

卷积神经网络 卷积(计算机科学) 计算机科学 人工智能 计算机视觉 人工神经网络
作者
Xin Zhang,Yingze Song,Tingting Song,Degang Yang,Yichen Ye,Jie Zhou,Liming Zhang
出处
期刊:Image and Vision Computing [Elsevier BV]
卷期号:149: 105190-105190 被引量:161
标识
DOI:10.1016/j.imavis.2024.105190
摘要

Neural networks based on convolutional operations have achieved remarkable results in the field of deep learning, but there are two inherent flaws in standard convolutional operations. On the one hand, the convolution operation is confined to a local window, so it cannot capture information from other locations, and its sampled shapes is fixed. On the other hand, the size of the convolutional kernel is fixed to k × k, which is a fixed square shape, and the number of parameters tends to grow squarely with size. Although Deformable Convolution (Deformable Conv) address the problem of fixed sampling of standard convolutions, the number of parameters also tends to grow in a squared manner, and Deformable Conv do not explore the effect of different initial sample shapes on network performance. In response to the above questions, the Linear Deformable Convolution (LDConv) is explored in this work, which gives the convolution kernel an arbitrary number of parameters and arbitrary sampled shapes to provide richer options for the trade-off between network overhead and performance. In LDConv, a novel coordinate generation algorithm is defined to generate different initial sampled positions for convolutional kernels of arbitrary size. To adapt to changing targets, offsets are introduced to adjust the shape of the samples at each position. LDConv corrects the growth trend of the number of parameters for standard convolution and Deformable Conv to a linear growth. Compared to Deformable Conv, LDConv provides richer choices and can be equivalent to deformable convolution when the number of parameters of LDConv is set to the square of K. Differently, this paper also explores the effect of neural networks by using LDConv with the same size and different initial sampling shapes. LDConv completes the process of efficient feature extraction by irregular convolutional operations and brings more exploration options for convolutional sampled shapes. Object detection experiments on representative datasets COCO2017, VOC 7 + 12, and VisDrone-DET2021 fully demonstrate the advantages of LDConv. LDConv is a plug-and-play convolutional operation that can replace the convolutional operation to improve network performance. The code for the relevant tasks can be found at https://github.com/CV-ZhangXin/LDConv.
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
平常寒烟发布了新的文献求助10
1秒前
沉默的从安完成签到,获得积分10
1秒前
2秒前
蝈蝈崽完成签到,获得积分10
2秒前
3秒前
无花果的应助被霍则风采纳,获得20
4秒前
4秒前
4秒前
秋风的应助被霍则风采纳,获得10
4秒前
秋风的应助被霍则风采纳,获得20
4秒前
我是老大的应助被坚强孤容采纳,获得10
4秒前
秋风的应助被霍则风采纳,获得20
4秒前
xing_xing的应助被霍则风采纳,获得20
4秒前
秋风的应助被霍则风采纳,获得20
4秒前
xing_xing的应助被霍则风采纳,获得100
4秒前
秋风的应助被霍则风采纳,获得20
4秒前
微笑的应助被霍则风采纳,获得20
5秒前
无极微光的应助被霍则风采纳,获得20
5秒前
5秒前
现代丸子完成签到 ,获得积分10
5秒前
耕者天下完成签到,获得积分10
5秒前
DW的应助被bqk采纳,获得10
6秒前
汉堡包的应助被着急的青枫采纳,获得10
6秒前
田様的应助被沉默的从安采纳,获得10
7秒前
平常寒烟完成签到,获得积分10
7秒前
高贵的平松完成签到,获得积分10
7秒前
SciGPT的应助被每天都好困采纳,获得10
8秒前
liuqc发布了新的文献求助10
8秒前
XXxx完成签到,获得积分10
8秒前
zhishui发布了新的文献求助10
9秒前
英俊的铭的应助被KimGyuvin采纳,获得10
10秒前
天天快乐的应助被子夜歌采纳,获得10
11秒前
星星完成签到,获得积分10
11秒前
Esther发布了新的文献求助10
11秒前
pillowdamon完成签到,获得积分10
12秒前
zhishui完成签到,获得积分10
14秒前
15秒前
16秒前
17秒前
CONG1完成签到,获得积分10
17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 8186784
求助须知:如何正确求助?哪些是违规求助? 9575092
关于积分的说明 21839541
捐赠科研通 7784418
什么是DOI,文献DOI怎么找? 3434819
关于科研通互助平台的介绍 2559221
邀请新用户注册赠送积分活动 2481682