Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
8.3
4.2
Journals
Remote Sensing
Special Issues
Advanced Techniques in Remote Sensing for Object Detection: From Few-Shot...
remotesensing-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Remote Sensing Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Advanced Techniques in Remote Sensing for Object Detection: From Few-Shot Learning to Open Vocabulary Applications

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing Image Processing".

Deadline for manuscript submissions: 31 December 2024 | Viewed by 2119

Special Issue Editors

Dr. Yin Zhuang

E-Mail Website
Guest Editor
National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing (SBIIP), Beijing Institute of Technology, Beijing 100081, China
Interests: representation learning; object detection; few-shot learning; semantic segmentation
Dr. Guanqun Wang

E-Mail Website
Guest Editor
National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing 100871, China
Interests: remote sensing object detection; multimodal large language models (MLLM); domain adaptation
Dr. Boya Zhao

E-Mail Website
Guest Editor
Key Laboratory of Computational Optical Imaging Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
Interests: object detection; onboard processing; multimodal fusion
Dr. Yue Zhang

E-Mail Website
Guest Editor
School of Digital Media and Design Arts, Beijing University of Posts and Telecommunications, Beijing 100876, China
Interests: object detection; multimodal learning; machine learning foundation model
Special Issues, Collections and Topics in MDPI journals
Dr. Wenjia Xu

E-Mail Website
Guest Editor
School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100083, China
Interests: few-shot learning; open-world recognition; remote sensing

Special Issue Information

Dear Colleagues,

The rapid advancement of remote sensing technologies and machine learning has opened up new avenues for the detection and analysis of objects in remote sensing images. This Special Issue is dedicated to exploring cutting-edge methodologies that enhance the ability of remote sensing to perform object detection through innovative learning frameworks and cross-domain applications.

We aim to showcase research that addresses critical challenges in remote sensing, with a focus on the following areas of interest:

  • Few-Shot Learning for Remote Sensing Data: Developing models that effectively learn from limited labeled data to perform generalization across diverse remote sensing datasets well.
  • Domain Adaptation in Remote Sensing: Enhancing the robustness of remote sensing models by enabling them to adapt across different domains, overcoming the challenges posed by the variability in environmental conditions and sensor specifications.
  • Open Vocabulary Object Detection: Exploring methodologies that enable the detection of previously undefined or rare objects in remote sensing images, thus broadening the scope of detectable features without extensive retraining.
  • Representation Learning from Remote Sensing Data: Investigating innovative approaches to represent and extract meaningful features from remote sensing data that significantly enhance the accuracy and efficiency of object detection.
  • Pre-Training Methods for Object Detection Models: Examining strategies that facilitate the pre-training of models on diverse datasets to enhance their performance and adaptability in object detection tasks within remote sensing contexts.
  • Advanced Multi-Temporal Change Detection: Finding critical changed information from multi-temporal remote sensing images that experience very complicated background interferences.

Contributions may include novel theoretical approaches, practical applications, and comprehensive reviews that contribute to the fields of environmental monitoring, urban planning, agricultural assessment, and beyond. We encourage submissions that not only present significant research findings, but also demonstrate the practical implications and applications of these advanced remote sensing techniques.

This Special Issue aims to gather contributions detailing diverse perspectives and methodologies in order to advance the boundaries of remote sensing in object detection, thus offering both insights into fundamental processes and frameworks for applied sciences.

Dr. Yin Zhuang
Dr. Guanqun Wang
Dr. Boya Zhao
Dr. Yue Zhang
Dr. Wenjia Xu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • object detection
  • few-shot learning
  • open vocabulary
  • model pretraining
  • domain adaptation
  • representation learning
  • change detection

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (2 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

19 pages, 5592 KiB  
Article
Hierarchical Mixed-Precision Post-Training Quantization for SAR Ship Detection Networks
by Hang Wei, Zulin Wang and Yuanhan Ni
Remote Sens. 2024, 16(21), 4042; https://doi.org/10.3390/rs16214042 - 30 Oct 2024
Viewed by 453
Abstract
Convolutional neural network (CNN)-based synthetic aperture radar (SAR) ship detection models operating directly on satellites can reduce transmission latency and improve real-time surveillance capabilities. However, limited satellite platform resources present a significant challenge. Post-training quantization (PTQ) provides an efficient method for pre-training neural [...] Read more.
Convolutional neural network (CNN)-based synthetic aperture radar (SAR) ship detection models operating directly on satellites can reduce transmission latency and improve real-time surveillance capabilities. However, limited satellite platform resources present a significant challenge. Post-training quantization (PTQ) provides an efficient method for pre-training neural networks to effectively reduce memory and computational resources without retraining. Despite this, PTQ faces the challenge of maintaining model accuracy, especially at low-bit quantization (e.g., 4-bit or 2-bit). To address this challenge, we propose a hierarchical mixed-precision post-training quantization (HMPTQ) method for SAR ship detection neural networks to reduce quantization error. This method encompasses a layerwise precision configuration based on reconstruction error and an intra-layer mixed-precision quantization strategy. Specifically, our approach initially utilizes the activation reconstruction error of each layer to gauge the sensitivity necessary for bit allocation, considering the interdependencies among layers, which effectively reduces the complexity of computational sensitivity and achieves more precise quantization allocation. Subsequently, to minimize the quantization error of the layers, an intra-layer mixed-precision quantization strategy based on probability density assigns a greater number of quantization bits to regions where the probability density is low for higher values. Our evaluation on the SSDD, HRSID, and LS-SSDD-v1.0 SAR Ship datasets, using different detection CNN models, shows that the YOLOV9c model with mixed-precision quantization at 4-bit and 2-bit for weights and activations achieves only a 0.28% accuracy loss on the SSDD dataset, while reducing the model size by approximately 80%. Compared to state-of-the-art methods, our approach maintains competitive accuracy, confirming the superior performance of the HMPTQ method over existing quantization techniques. Full article
(This article belongs to the Special Issue Advanced Techniques in Remote Sensing for Object Detection: From Few-Shot Learning to Open Vocabulary Applications)
►▼ Show Figures

Figure 1

26 pages, 6045 KiB  
Article
Q-A2NN: Quantized All-Adder Neural Networks for Onboard Remote Sensing Scene Classification
by Ning Zhang, He Chen, Liang Chen, Jue Wang, Guoqing Wang and Wenchao Liu
Remote Sens. 2024, 16(13), 2403; https://doi.org/10.3390/rs16132403 - 30 Jun 2024
Viewed by 1010
Abstract
Performing remote sensing scene classification (RSSC) directly on satellites can alleviate data downlink burdens and reduce latency. Compared to convolutional neural networks (CNNs), the all-adder neural network (A2NN) is a novel basic neural network that is more suitable for onboard RSSC, [...] Read more.
Performing remote sensing scene classification (RSSC) directly on satellites can alleviate data downlink burdens and reduce latency. Compared to convolutional neural networks (CNNs), the all-adder neural network (A2NN) is a novel basic neural network that is more suitable for onboard RSSC, enabling lower computational overhead by eliminating multiplication operations in convolutional layers. However, the extensive floating-point data and operations in A2NNs still lead to significant storage overhead and power consumption during hardware deployment. In this article, a shared scaling factor-based de-biasing quantization (SSDQ) method tailored for the quantization of A2NNs is proposed to address this issue, including a powers-of-two (POT)-based shared scaling factor quantization scheme and a multi-dimensional de-biasing (MDD) quantization strategy. Specifically, the POT-based shared scaling factor quantization scheme converts the adder filters in A2NNs to quantized adder filters with hardware-friendly integer input activations, weights, and operations. Thus, quantized A2NNs (Q-A2NNs) composed of quantized adder filters have lower computational and memory overheads than A2NNs, increasing their utility in hardware deployment. Although low-bit-width Q-A2NNs exhibit significantly reduced RSSC accuracy compared to A2NNs, this issue can be alleviated by employing the proposed MDD quantization strategy, which combines a weight-debiasing (WD) strategy, which reduces performance degradation due to deviations in the quantized weights, with a feature-debiasing (FD) strategy, which enhances the classification performance of Q-A2NNs through minimizing deviations among the output features of each layer. Extensive experiments and analyses demonstrate that the proposed SSDQ method can efficiently quantize A2NNs to obtain Q-A2NNs with low computational and memory overheads while maintaining comparable performance to A2NNs, thus having high potential for onboard RSSC. Full article
(This article belongs to the Special Issue Advanced Techniques in Remote Sensing for Object Detection: From Few-Shot Learning to Open Vocabulary Applications)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop