BiShuffleNeXt: A lightweight bi-path network for remote sensing scene classification

Chen, Zhichao; Yang, Jie; Feng, Zhicheng; Chen, Lifang; Li, Linhong

doi:10.1016/j.measurement.2023.112537

Cited by 17 publications

(6 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed method exhibits a higher OA in NWPU datasets with training ratios of 10% and 20%, yielding 91.42% and 93.83%, respectively. For certain approaches that involve training train CNN models from scratch, several options include MIDC-Net-CS [47], MSA-Network [46], PSGAN [54], ACR-MLFF [53], MSRes-SplitNet [19], T-CNN [55], and BiShuf-fleNext [51], LPNet proves superior. Moreover, our LPNet surpasses several methods using classical CNNs plus gating mechanisms, including Alex+SAFF [49], ResNet-50+EAM [42], and Alex-MS2AP [43].…”

Section: Experiments Results and Analysis On Nwpumentioning

confidence: 99%

“…Furthermore, the OA of all the methods on the AID dataset is lower than that of the UCM dataset. Despite this, advanced methods such as Alex‐SAFF [49], MIDC‐Net‐CS [47], LCPP [50], DA2Net [45], BiShuffleNext [51], CIPAL [52], and PSGAN [54] are proposed to address existing difficulties in remote sensing images, but they have achieved lower classification accuracy than our LPNet. Some techniques, like Alex‐MS2AP [43] and ACR‐MLFF [53], have shown superior performance on AID at training ratios of 20% compared to LPNet.…”

Section: Experiments and Analysismentioning

confidence: 99%

See 1 more Smart Citation

LPNet: A remote sensing scene classification method based on large kernel convolution and parameter fusion

Wang,

Shi,

Wang

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

Remote sensing scene images contain numerous feature targets with unrelated semantic information, so how to extract to the local key information and semantic features of the image becomes the key to achieving accurate classification. Existing Convolutional Neural Networks (CNNs) mostly concentrate on the global representation of an image and lose the shallow features. To overcome these issues, this paper proposes LPNet for remote sensing scene image classification. First, LPNet employs LKConv to extract the semantic features in the image, while using standard convolution to extract local key information in the image. Additionally, the LPNet applies a shortcut residual concatenation branch to reuse features. Then, parameter fusion combines parameters from previous branches, improving the capacity of the model to obtain a more comprehensive and rich feature representation of the image. Finally, considering the relationship between the classification ability of the model and the depth of feature extraction, the Feature Mixture (FM) Block is used to deepen the model for feature extraction. Comparative experiments on four publicly available datasets show that LPNet provides comparable results to other state‐of‐the‐art methods. The effectiveness of LPNet is further demonstrated by visualizing the effective receptive fields (ERFs).

show abstract

Section: Experiments Results and Analysis On Nwpumentioning

confidence: 99%

Section: Experiments and Analysismentioning

confidence: 99%

LPNet: A remote sensing scene classification method based on large kernel convolution and parameter fusion

Wang,

Shi,

Wang

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Kang and Cha 21 expanded the data volume from 1203 to 12030 images by using Mix-Up and random cropping methods to synthesize the cracked images. Random cropping is a widely used enhancement in remote sensing image processing 22 , 23 , and its main purpose is to improve the diversity of images and the generalization ability of models. In addition, some illumination enhancement algorithms 24 are also widely used to adjust the illumination conditions of the images to generate more variable datasets.…”

Section: Related Workmentioning

confidence: 99%

RailFOD23: A dataset for foreign object detection on railroad transmission lines

Chen,

Yang,

Feng

et al. 2024

Sci Data

Self Cite

View full text Add to dashboard Cite

Artificial intelligence models play a crucial role in monitoring and maintaining railroad infrastructure by analyzing image data of foreign objects on power transmission lines. However, the availability of publicly accessible datasets for railroad foreign objects is limited, and the rarity of anomalies in railroad image data, combined with restricted data sharing, poses challenges for training effective foreign object detection models. In this paper, the aim is to present a new dataset of foreign objects on railroad transmission lines, and evaluating the overall performance of mainstream detection models in this context. Taking a unique approach and leveraging large-scale models such as ChatGPT (Chat Generative Pre-trained Transformer) and text-to-image generation models, we synthesize a series of foreign object data. The dataset includes 14,615 images with 40,541 annotated objects, covering four common foreign objects on railroad power transmission lines. Through empirical research on this dataset, we validate the performance of various baseline models in foreign object detection, providing valuable insights for the monitoring and maintenance of railroad facilities.

show abstract

“…Hui et al [33] introduce STF-YOLO, a novel UAV image detection algorithm that incorporates SwinTransformer with CNNs in a structure called STRCN and uses a lightweight classifier, CNeB, for enhanced accuracy. Chen et al [34] introduce BiShuffleNeXt, an efficient remote sensing scene classification model that utilizes a dual-path architecture with sandglass bottlenecks to enhance semantic and spatial information processing.…”

Section: Background and Related Literaturementioning

confidence: 99%

AeroDetectNet: a lightweight, high-precision network for enhanced detection of small objects in aerial remote sensing imagery

Bai,

Lu,

Zhang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Object detection in remote sensing imagery exhibits difficulties due to complex backgrounds, diverse object scales, and intricate spatial context relationships. Motivated by the problems mentioned above, this paper introduces AeroDetectNet, a novel lightweight and high-precision object detection network custom-designed for aerial remote sensing scenarios, building upon the YOLOv7-tiny algorithm. It enhances performance through four key improvements: the Normalized Wasserstein Distance for consistent object size sensitivity, the Involution module for reduced background noise, a self-designed RCS-Biformer module for better spatial context interpretation, and a self-designed WF-CoT SPPCSP feature pyramid for improved feature map weighting and context capture. Ablation studies conducted on a hybrid dataset composed of three open-source remote sensing datasets (including NWPU VHR-10 remote sensing images, RSOD remote sensing images, and VisDrone UAV images) have demonstrated the effectiveness of four improvements specifically for small-size object detection. Visualizations through Grad-CAM further demonstrate AeroDetectNet's capacity to extract and focus on key object features. Upon individual testing across three open-source datasets, AeroDetectNet has successfully demonstrated its ability to identify objects in images with a smaller pixel area. Through experimental comparisons with other related studies, the AeroDetectNet achieved a competitive mAP while maintaining fewer model parameters, highlighting its highly accurate and lightweight properties.

show abstract

BiShuffleNeXt: A lightweight bi-path network for remote sensing scene classification

Cited by 17 publications

References 25 publications

LPNet: A remote sensing scene classification method based on large kernel convolution and parameter fusion

LPNet: A remote sensing scene classification method based on large kernel convolution and parameter fusion

RailFOD23: A dataset for foreign object detection on railroad transmission lines

AeroDetectNet: a lightweight, high-precision network for enhanced detection of small objects in aerial remote sensing imagery

Contact Info

Product

Resources

About