An Explainable Spatial–Frequency Multiscale Transformer for Remote Sensing Scene Classification

Yang, Yuting; Jiao, Licheng; Liu, Fang; Liu, Xu; Chen, Puhua; Yang, Shuyuan

doi:10.1109/tgrs.2023.3265361

Cited by 15 publications

(12 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the two leading methods (Zhang et al. , 2021b; Yang et al. , 2023) for the AID set do not present exciting performances on the NWPU set.…”

Section: Resultsmentioning

confidence: 95%

“…Compared to the other previous methods, we can find that the most confusing categories are commonly the same as MBC-Net, though the methods' OA is generally lower. In particular, for those ViT methods with a higher OA (Zhang et al ., 2021b; Yang et al ., 2023), some different clues should be mentioned. E.g., the first method has the most confusing categories of nature scenes.…”

Section: Resultsmentioning

confidence: 99%

“…In particular, some tests (Wang et al, 2023b) prove that a ViT is inferior to a CNN if the RSI training sets only have fewer finite samples. In addition, Yang et al (2023) and Ma et al (2022) also proposed two different methods to verify the effectiveness of combined ViT models. These two creative approaches, based only on the method's accuracy, still lack breakthroughs.…”

Section: Related Workmentioning

confidence: 99%

“…, 2023b) prove that a ViT is inferior to a CNN if the RSI training sets only have fewer finite samples. In addition, Yang et al. (2023) and Ma et al.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

MBC-Net: long-range enhanced feature fusion for classifying remote sensing images

Song

2023

IJICC

View full text Add to dashboard Cite

PurposeClassification of remote sensing images (RSI) is a challenging task in computer vision. Recently, researchers have proposed a variety of creative methods for automatic recognition of RSI, and feature fusion is a research hotspot for its great potential to boost performance. However, RSI has a unique imaging condition and cluttered scenes with complicated backgrounds. This larger difference from nature images has made the previous feature fusion methods present insignificant performance improvements.Design/methodology/approachThis work proposed a two-convolutional neural network (CNN) fusion method named main and branch CNN fusion network (MBC-Net) as an improved solution for classifying RSI. In detail, the MBC-Net employs an EfficientNet-B3 as its main CNN stream and an EfficientNet-B0 as a branch, named MC-B3 and BC-B0, respectively. In particular, MBC-Net includes a long-range derivation (LRD) module, which is specially designed to learn the dependence of different features. Meanwhile, MBC-Net also uses some unique ideas to tackle the problems coming from the two-CNN fusion and the inherent nature of RSI.FindingsExtensive experiments on three RSI sets prove that MBC-Net outperforms the other 38 state-of-the-art (STOA) methods published from 2020 to 2023, with a noticeable increase in overall accuracy (OA) values. MBC-Net not only presents a 0.7% increased OA value on the most confusing NWPU set but also has 62% fewer parameters compared to the leading approach that ranks first in the literature.Originality/valueMBC-Net is a more effective and efficient feature fusion approach compared to other STOA methods in the literature. Given the visualizations of grad class activation mapping (Grad-CAM), it reveals that MBC-Net can learn the long-range dependence of features that a single CNN cannot. Based on the tendency stochastic neighbor embedding (t-SNE) results, it demonstrates that the feature representation of MBC-Net is more effective than other methods. In addition, the ablation tests indicate that MBC-Net is effective and efficient for fusing features from two CNNs.

show abstract

“…In addition, the two leading methods (Zhang et al. , 2021b; Yang et al. , 2023) for the AID set do not present exciting performances on the NWPU set.…”

Section: Resultsmentioning

confidence: 95%

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…, 2023b) prove that a ViT is inferior to a CNN if the RSI training sets only have fewer finite samples. In addition, Yang et al. (2023) and Ma et al.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

MBC-Net: long-range enhanced feature fusion for classifying remote sensing images

Song

2023

IJICC

View full text Add to dashboard Cite

show abstract

“…In a similar vein, some researchers (Shen et al, 2022b;Tang et al, 2021;Wang et al, 2022b;Xu et al, 2022aXu et al, , 2022bXu et al, , 2022cXu et al, , 2022d proposed parallel multi-model methods that incorporate two CNNs. Moreover, some other researchers (Deng et al, 2022;Ma et al, 2022;Wang et al, 2023aWang et al, , 2023bYang et al, 2023;Zhang et al, 2021;Zhao et al, 2023) proposed more complex multimodel methods by combining CNNs and ViTs. However, even when disregarding larger model volumes, only a few of these multi-model methods have demonstrated competitive performance.…”

Section: Related Workmentioning

confidence: 99%

Efficient knowledge distillation for remote sensing image classification: a CNN-based approach

Song,

Wei,

Yong

2023

IJWIS

View full text Add to dashboard Cite

Purpose The paper aims to tackle the classification of Remote Sensing Images (RSIs), which presents a significant challenge for computer algorithms due to the inherent characteristics of clustered ground objects and noisy backgrounds. Recent research typically leverages larger volume models to achieve advanced performance. However, the operating environments of remote sensing commonly cannot provide unconstrained computational and storage resources. It requires lightweight algorithms with exceptional generalization capabilities. Design/methodology/approach This study introduces an efficient knowledge distillation (KD) method to build a lightweight yet precise convolutional neural network (CNN) classifier. This method also aims to substantially decrease the training time expenses commonly linked with traditional KD techniques. This approach entails extensive alterations to both the model training framework and the distillation process, each tailored to the unique characteristics of RSIs. In particular, this study establishes a robust ensemble teacher by independently training two CNN models using a customized, efficient training algorithm. Following this, this study modifies a KD loss function to mitigate the suppression of non-target category predictions, which are essential for capturing the inter- and intra-similarity of RSIs. Findings This study validated the student model, termed KD-enhanced network (KDE-Net), obtained through the KD process on three benchmark RSI data sets. The KDE-Net surpasses 42 other state-of-the-art methods in the literature published from 2020 to 2023. Compared to the top-ranked method’s performance on the challenging NWPU45 data set, KDE-Net demonstrated a noticeable 0.4% increase in overall accuracy with a significant 88% reduction in parameters. Meanwhile, this study’s reformed KD framework significantly enhances the knowledge transfer speed by at least three times. Originality/value This study illustrates that the logit-based KD technique can effectively develop lightweight CNN classifiers for RSI classification without substantial sacrifices in computation and storage costs. Compared to neural architecture search or other methods aiming to provide lightweight solutions, this study’s KDE-Net, based on the inherent characteristics of RSIs, is currently more efficient in constructing accurate yet lightweight classifiers for RSI classification.

show abstract

A Multi-Scale Additive Enhanced Network for Remote Sensing Scene Classification

Wang,

Zhou,

Wang

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

An Explainable Spatial–Frequency Multiscale Transformer for Remote Sensing Scene Classification

Cited by 15 publications

References 61 publications

MBC-Net: long-range enhanced feature fusion for classifying remote sensing images

MBC-Net: long-range enhanced feature fusion for classifying remote sensing images

Efficient knowledge distillation for remote sensing image classification: a CNN-based approach

A Multi-Scale Additive Enhanced Network for Remote Sensing Scene Classification

Contact Info

Product

Resources

About