A Meta-Analysis of Convolutional Neural Networks for Remote Sensing Applications

Ghanbari, Hamid; Mahdianpari, Masoud; Homayouni, Saeid; Mohammadimanesh, Fariba

doi:10.1109/jstars.2021.3065569

Cited by 40 publications

(20 citation statements)

References 129 publications

(148 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the focus of current literature has been shifted to multi-scale and fusion methods in the scene image classification domain, and existing deep learning methods are making full use of multi-scale information and fusion for better representation. For instance, Ghanbari et al [34] proposed a multi-scale method called dense-global-residual network to reduce the loss of spatial information and enhance the context information. The authors used a residual network to extract the features and a global spatial pyramid pooling module to obtain dense multi-scale features at different levels.…”

Section: Literature Reviewmentioning

confidence: 99%

Patch-Based Discriminative Learning for Remote Sensing Scene Classification

Usman¹,

Hoque²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>The bag-of-words (BoW) model is one of the most popular representation methods for image classification. However, the lack of spatial information, the intra-class diversity, and the inter-class similarity among scene categories impair its performance in the remote-sensing domain. To alleviate these issues, this paper proposes to explore the spatial dependencies between different image regions and introduces patch-based discriminative learning (PBDL) for remote-sensing scene classification. Particularly, the proposed method employs multi-level feature learning based on small, medium, and large neighborhood regions to enhance the discriminative power of image representation. To achieve this, image patches are selected through a fixed-size sliding window and sampling redundancy, a novel concept, is developed to minimize the redundant features while sustaining the relevant features for the model. Apart from multi-level learning, we explicitly impose image pyramids to magnify the visual information of the scene images and optimize their position and scale parameters locally. Motivated by this, a local descriptor is exploited to extract multi-level and multi-scale features that we represent in terms of codewords histogram by performing k-means clustering. Finally, a simple fusion strategy is proposed to balance the contribution of individual features, and the fused features are incorporated into a Bidirectional Long Short-Term Memory (BiLSTM) network for classification. Experimental results on NWPU-RESISC45, AID, UC-Merced, and WHU-RS datasets demonstrate that the proposed approach not only surpasses the conventional bag-of-words approaches but also yields significantly higher classification performance than the existing state-of-the-art deep learning methods used nowadays.</p>

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Patch-Based Discriminative Learning for Remote Sensing Scene Classification

Usman¹,

Hoque²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…[11,12] reviewed 429 studies to investigate the impact of DL for earth observation applications through image segmentation and object detection; ref. [13] reviewed 416 papers in a meta-analysis and discussed the distribution of data sensors, DL models and application types in those studies; refs. [14,15] reviewed the deep learning applications for scene classification on aspects of the challenges, methods, benchmarks and opportunities.…”

Section: Introductionmentioning

confidence: 99%

“…Since the introduction of DL to the RS community, it has been widely adopted to solve a variety of RS tasks in classification, segmentation and object detection, and a few relevant review articles were published relevant to DLbased RS applications. For example, [2] reviewed the DL models for road extraction during the time period from 2010 to 2019; [3] discussed data sources, data preparation, training details and performance comparison for DL semantic segmentation models for satellite images in urban environments; [4], [5] reviewed DL applications in hyperspectral and multispectral images; [6], [7] reviewed DL approaches to process 3D point cloud or RS data; [8] reviewed various applications based on DL models including detection and segmentation of individual plants and vegetation classes; [9] broadly reviewed applications of DL models on various RS tasks including image preprocessing, change detection and classification; [10] discussed various DL models used for wetland mapping; [11], [12] reviewed 429 studies to investigate the impact of DL for earth observation applications through image segmentation and object detection; [13] reviewed 416 papers in a meta-analysis and discussed the distribution of data sensors, DL models and application types in those studies; [14,15] reviewed the deep learning applications for scene classification on aspects of the challenges, methods, benchmarks and opportunities.…”

Section: Introductionmentioning

confidence: 99%

A Review of Landcover Classification with Very-High Resolution Remotely Sensed Optical Images—Analysis Unit, Model Scalability and Transferability

Qin

Liu

2022

Remote Sensing

View full text Add to dashboard Cite

As an important application in remote sensing, landcover classification remains one of the most challenging tasks in very-high-resolution (VHR) image analysis. As the rapidly increasing number of Deep Learning (DL) based landcover methods and training strategies are claimed to be the state-of-the-art, the already fragmented technical landscape of landcover mapping methods has been further complicated. Although there exists a plethora of literature review work attempting to guide researchers in making an informed choice of landcover mapping methods, the articles either focus on the review of applications in a specific area or revolve around general deep learning models, which lack a systematic view of the ever advancing landcover mapping methods. In addition, issues related to training samples and model transferability have become more critical than ever in an era dominated by data-driven approaches, but these issues were addressed to a lesser extent in previous review articles regarding remote sensing classification. Therefore, in this paper, we present a systematic overview of existing methods by starting from learning methods and varying basic analysis units for landcover mapping tasks, to challenges and solutions on three aspects of scalability and transferability with a remote sensing classification focus including (1) sparsity and imbalance of data; (2) domain gaps across different geographical regions; and (3) multi-source and multi-view fusion. We discuss in detail each of these categorical methods and draw concluding remarks in these developments and recommend potential directions for the continued endeavor.

show abstract

“…eal-time target detection is an essential task of intelligent remote sensing satellite systems, which are exhibiting rapid development [1]. Target detection models based on deep convolutional neural networks [2,3] can extract features effectively and have resulted in breakthroughs in remote sensing image processing [4,5]. However, models with better performances typically have deeper neural network structures and a large number of parameters, increasing the model's inference time and requiring extensive computational resources.…”

Section: Introductionmentioning

confidence: 99%

Target Detection Model Distillation Using Feature Transition and Label Registration for Remote Sensing Imagery

Zhao

Wang

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Deep convolution networks have been widely used in remote sensing target detection for various applications in recent years. Target detection models with many parameters provide better results but are not suitable for resource-constrained devices due to their high computational cost and storage requirements. Furthermore, current lightweight target detection models for remote sensing imagery rarely have the advantages of existing models. Knowledge distillation can improve the learning ability of a small student network from a large teacher network due to acceleration and compression. However, current knowledge distillation methods typically use mature backbones as teacher and student networks are unsuitable for target detection in remote sensing imagery. In this paper, we propose a target detection model distillation (TDMD) framework using feature transition and label registration for remote sensing imagery. A lightweight attention network is designed by ranking the importance of the convolutional feature layers in the teacher network. Multi-scale feature transition based on a feature pyramid is utilized to constrain the feature maps of the student network. A label registration procedure is proposed to improve the TDMD model's learning ability of the output distribution of the teacher network. The proposed method is evaluated on the DOTA and NWPU VHR-10 remote sensing image datasets. The results show that the TDMD achieves a mean Average Precision (mAP) of 75.47% and 93.81% on the DOTA and NWPU VHR-10 datasets, respectively. Moreover, the model size is 43% smaller than that of the predecessor model (11.8 MB and 11.6 MB for the two datasets).

show abstract

A Meta-Analysis of Convolutional Neural Networks for Remote Sensing Applications

Cited by 40 publications

References 129 publications

Patch-Based Discriminative Learning for Remote Sensing Scene Classification

Patch-Based Discriminative Learning for Remote Sensing Scene Classification

A Review of Landcover Classification with Very-High Resolution Remotely Sensed Optical Images—Analysis Unit, Model Scalability and Transferability

Target Detection Model Distillation Using Feature Transition and Label Registration for Remote Sensing Imagery

Contact Info

Product

Resources

About