Middle-Level Feature Fusion for Lightweight RGB-D Salient Object Detection

计算机科学 人工智能 特征提取 特征(语言学) RGB颜色模型 情态动词 模式识别(心理学) 水准点(测量) 子网 目标检测 计算机视觉 保险丝(电气) 融合 工程类 电气工程 地理 哲学 语言学 化学 计算机安全 大地测量学 高分子化学
作者
Nianchang Huang,Qiang Jiao,Qiang Zhang,Jungong Han
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:31: 6621-6634 被引量:67
标识
DOI:10.1109/tip.2022.3214092
摘要

Most existing RGB-D salient object detection (SOD) models adopt a two-stream structure to extract the information from the input RGB and depth images. Since they use two subnetworks for unimodal feature extraction and multiple multi-modal feature fusion modules for extracting cross-modal complementary information, these models require a huge number of parameters, thus hindering their real-life applications. To remedy this situation, we propose a novel middle-level feature fusion structure that allows to design a lightweight RGB-D SOD model. Specifically, the proposed structure first employs two shallow subnetworks to extract low- and middle-level unimodal RGB and depth features, respectively. Afterward, instead of integrating middle-level unimodal features multiple times at different layers, we just fuse them once via a specially designed fusion module. On top of that, high-level multi-modal semantic features are further extracted for final salient object detection via an additional subnetwork. This will greatly reduce the network's parameters. Moreover, to compensate for the performance loss due to parameter deduction, a relation-aware multi-modal feature fusion module is specially designed to effectively capture the cross-modal complementary information during the fusion of middle-level multi-modal features. By enabling the feature-level and decision-level information to interact, we maximize the usage of the fused cross-modal middle-level features and the extracted cross-modal high-level features for saliency prediction. Experimental results on several benchmark datasets verify the effectiveness and superiority of the proposed method over some state-of-the-art methods. Remarkably, our proposed model has only 3.9M parameters and runs at 33 FPS.
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
刚刚
Liew完成签到 ,获得积分10
1秒前
zo发布了新的文献求助10
1秒前
甜美沛容发布了新的文献求助10
1秒前
1秒前
2秒前
木子发布了新的文献求助10
3秒前
3秒前
3秒前
3秒前
4秒前
4秒前
冷傲的白柏完成签到,获得积分10
5秒前
霁月发布了新的文献求助10
6秒前
6秒前
自由的雪一完成签到,获得积分10
6秒前
7秒前
Olive发布了新的文献求助10
7秒前
完美世界的应助被六月雪采纳,获得10
8秒前
8秒前
霁月发布了新的文献求助10
9秒前
9秒前
霁月发布了新的文献求助10
9秒前
霁月发布了新的文献求助10
9秒前
霁月发布了新的文献求助10
9秒前
ZZKKZZ发布了新的文献求助10
9秒前
10秒前
10秒前
11秒前
12秒前
13秒前
所所的应助被dieeee采纳,获得10
13秒前
科研通AI2S的应助被清秀千兰采纳,获得10
14秒前
14秒前
小SCI发布了新的文献求助10
14秒前
14秒前
15秒前
uu发布了新的文献求助10
15秒前
15秒前
15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
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 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 8183694
求助须知:如何正确求助?哪些是违规求助? 9572963
关于积分的说明 21828306
捐赠科研通 7780864
什么是DOI,文献DOI怎么找? 3434057
关于科研通互助平台的介绍 2558257
邀请新用户注册赠送积分活动 2480541