相关实验视频

Updated: Jul 9, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

UTDNet: 一个统一的三重解码器网络,用于多模式突出物体检测

Fushuo Huo¹, Ziming Liu¹, Jingcai Guo¹

¹Department of Computing, The Hong Kong Polytechnic University, Hong Kong Special Administrative Region of China.

Neural networks : the official journal of the International Neural Network Society

|December 3, 2023

概括

一个新的统一三位式解码器网络 (UTDNet) 能够在单个模型中使用RGB-T和RGB-D数据进行准确的突出物体检测 (SOD). 这种方法克服了现有方法的局限性,改善了实际应用.

科学领域:

计算机视觉计算机视觉
图像处理图像处理

背景情况:

突出物体检测 (SOD) 在计算机视觉中至关重要.
多模式数据 (RGB,深度,热) 增强了SOD.
现有的方法仅限于特定的模式 (RGB-D或RGB-T) 或需要特定的数据集微调,阻碍实际使用.

研究的目的:

为RGB-T和RGB-DSOD任务提出一个端到端的统一三元解码器网络 (UTDNet).
为了应对统一的多式联运SOD的挑战:准确的突出物体检测和一个单一的网络用于多种模式.
改进SOD在现实应用中的实际部署.

主要方法:

开发了一个多尺度的特征提取单元,以丰富上下文信息.
引入了一种高效的融合模块,用于探索跨模式的补充信息.
实现了三重解码器,具有层次深度监督损失,用于突出物体检测.
使用了带有弹性重量巩固 (EWC) 正规化的持续学习方法来统一多式联网SOD任务,而不需要额外的参数.

主要成果:

UTDNet有效地检测和分段突出物体在不同的模式.
提出的持续学习方法成功地将RGB-T和RGB-D SOD任务统一到一个单一网络中.
三重解码器架构通过将任务特定信息和任务不变信息分开,方便适应各种多式联网SOD任务.
广泛的比较显示UTDNet的性能优于最近26种RGB-T和RGB-D SOD方法.

结论:

UTDNet为多式联络突出物体检测提供了一个优越的,统一的解决方案.
网络的设计提高了实际SOD应用的准确性和适应性.
这项工作通过实现高效和多用途的多式联运SOD,推动了该领域的发展.

关键词:

多模式融合多模式融合突出物体检测突出物体检测统一的模型统一的模型

更多相关视频

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

相关概念视频

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...

Deconvolution

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...

Force Classification

Force Classification

Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...