A Lightweight and Robust Lie Group-Convolutional Neural Networks Joint Representation for Remote Sensing Scene Classification

Xu, Chengjun; Zhu, Guobin; Shu, Jingqian

doi:10.1109/tgrs.2020.3048024

Cited by 57 publications

(43 citation statements)

References 97 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the results are shown in Table 1, using three feature maps still achieves the best performance. Regarding the model complexity, using the proposed Multihead attention layer with three feature maps increases the model footprint from 4.6 M to 9.4 M. To meet the constrain of maximum 5 M of trainable parameters, we apply the quantization technique which [43] 89.4 91.7 MG-CAP (Bilinear) (55.99 M) [43] 89.4 93.0 MG-CAP (Sqrt-E) (55.99 M) [43] 90.8 93.0 EfficientNet-B0-aux (≈ 5.3𝑀) [2] 90.0 92.9 EfficientNet-B3-aux (≈ 13𝑀) [2] 91.1 93.8 VGG-16 + MTL (≈ 138.4 M) [62] -91.5 ResNeXt-50 + MTL (≈ 25 M) [62] -93.8 ResNeXt-101 + MTL (≈ 88.79 M) [62] 91.9 94.2 SE-MDPMNet (5.17 M) [54] 91.8 94.1 LGRIN (4.63 M) [49] 91.9 94.4 Transformer (46.3 M) [57] 93.1 95.6 Our systems (2.4 M) 91.0 93.8…”

Section: Resultsmentioning

confidence: 99%

A Robust and Low Complexity Deep Learning Model for Remote Sensing Image Classification

Cam¹,

Pham²,

Nvn³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper, we present a robust and low complexity deep learning model for Remote Sensing Image Classification (RSIC), the task of identifying the scene of a remote sensing image. In particular, we firstly evaluate different low complexity and benchmark deep neural networks: MobileNetV1, MobileNetV2, NASNetMobile, and EfficientNetB0, which present the number of trainable parameters lower than 5 Million (M). After indicating best network architecture, we further improve the network performance by applying attention schemes to multiple feature maps extracted from middle layers of the network. To deal with the issue of increasing the model footprint as using attention schemes, we apply the quantization technique to satisfies the number trainable parameter of the model lower than 5 M. By conducting extensive experiments on the benchmark datasets NWPU-RESISC45, we achieve a robust and low-complexity model, which is very competitive to the state-of-the-art systems and potential for real-life applications on edge devices.

show abstract

Section: Resultsmentioning

confidence: 99%

A Robust and Low Complexity Deep Learning Model for Remote Sensing Image Classification

Cam¹,

Pham²,

Nvn³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The coefficient vectors A and C are used to calculate Eqs. (10) and (11). where a value is linearly reduced from 2 to 0 over the iterations and random number r in the range of [0, 1].…”

Section: Whale Optimization Algorithmmentioning

confidence: 99%

Optimal guidance whale optimization algorithm and hybrid deep learning networks for land use land cover classification

Vinaykumar¹,

Babu²,

Frnda

2023

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Satellite Image classification provides information about land use land cover (LULC) and this is required in many applications such as Urban planning and environmental monitoring. Recently, deep learning techniques were applied for satellite image classification and achieved higher efficiency. The existing techniques in satellite image classification have limitations of overfitting problems due to the convolutional neural network (CNN) model generating more features. This research proposes the optimal guidance-whale optimization algorithm (OG-WOA) technique to select the relevant features and reduce the overfitting problem. The optimal guidance technique increases the exploitation of the search technique by changing the position of the search agent related to the best fitness value. This increase in exploitation helps to select the relevant features and avoid overfitting problems. The input images are normalized and applied to AlexNet–ResNet50 model for feature extraction. The OG-WOA technique is applied in extracted features to select relevant features. Finally, the selected features are processed for classification using Bi-directional long short-term memory (Bi-LSTM). The proposed OG-WOA–Bi-LSTM technique has an accuracy of 97.12% on AID, 99.34% on UCM, and 96.73% on NWPU, SceneNet model has accuracy of 89.58% on AID, and 95.21 on the NWPU dataset.

show abstract

“…LGRIN [56], SCViT [53] and ET-GSNet [57] are single-branch networks. Specifically, the D-CNN [34] network leverages the metric learning scheme to learn discriminative features.…”

Section: Comparison With State Of the Artsmentioning

confidence: 99%

Scale‐wise interaction fusion and knowledge distillation network for aerial scene recognition

Ning

Lei

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

Aerial scene recognition (ASR) has attracted great attention due to its increasingly essential applications. Most of the ASR methods adopt the multi‐scale architecture because both global and local features play great roles in ASR. However, the existing multi‐scale methods neglect the effective interactions among different scales and various spatial locations when fusing global and local features, leading to a limited ability to deal with challenges of large‐scale variation and complex background in aerial scene images. In addition, existing methods may suffer from poor generalisations due to millions of to‐be‐learnt parameters and inconsistent predictions between global and local features. To tackle these problems, this study proposes a scale‐wise interaction fusion and knowledge distillation (SIF‐KD) network for learning robust and discriminative features with scale‐invariance and background‐independent information. The main highlights of this study include two aspects. On the one hand, a global‐local features collaborative learning scheme is devised for extracting scale‐invariance features so as to tackle the large‐scale variation problem in aerial scene images. Specifically, a plug‐and‐play multi‐scale context attention fusion module is proposed for collaboratively fusing the context information between global and local features. On the other hand, a scale‐wise knowledge distillation scheme is proposed to produce more consistent predictions by distilling the predictive distribution between different scales during training. Comprehensive experimental results show the proposed SIF‐KD network achieves the best overall accuracy with 99.68%, 98.74% and 95.47% on the UCM, AID and NWPU‐RESISC45 datasets, respectively, compared with state of the arts.

show abstract

A Lightweight and Robust Lie Group-Convolutional Neural Networks Joint Representation for Remote Sensing Scene Classification

Cited by 57 publications

References 97 publications

A Robust and Low Complexity Deep Learning Model for Remote Sensing Image Classification

A Robust and Low Complexity Deep Learning Model for Remote Sensing Image Classification

Optimal guidance whale optimization algorithm and hybrid deep learning networks for land use land cover classification

Scale‐wise interaction fusion and knowledge distillation network for aerial scene recognition

Contact Info

Product

Resources

About