TransMIN: Transformer-Guided Multi-Interaction Network for Remote Sensing Object Detection

Xu, G. S.; Song, Tianyou; Sun, Xia; Gao, Chenqiang

doi:10.1109/lgrs.2022.3230973

Cited by 8 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, the transformer [28], initially proposed for natural language processing (NLP), has garnered significant attention and has been applied in various computer vision domains [29,30]. The transformer introduces self-attention mechanisms to replace convolutional operators, thereby enabling models to better learn global contextual information from images.…”

Section: Transformer-based Methods For Road Extractionmentioning

confidence: 99%

Global–Local Information Fusion Network for Road Extraction: Bridging the Gap in Accurate Road Segmentation in China

Wang,

Cai,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Road extraction is crucial in urban planning, rescue operations, and military applications. Compared to traditional methods, using deep learning for road extraction from remote sensing images has demonstrated unique advantages. However, previous convolutional neural networks (CNN)-based road extraction methods have had limited receptivity and failed to effectively capture long-distance road features. On the other hand, transformer-based methods have good global information-capturing capabilities, but face challenges in extracting road edge information. Additionally, existing excellent road extraction methods lack validation for the Chinese region. To address these issues, this paper proposes a novel road extraction model called the global–local information fusion network (GLNet). In this model, the global information extraction (GIE) module effectively integrates global contextual relationships, the local information extraction (LIE) module accurately captures road edge information, and the information fusion (IF) module combines the output features from both global and local branches to generate the final extraction results. Further, a series of experiments on two different Chinese road datasets with geographic robustness demonstrate that our model outperforms the state-of-the-art deep learning models for road extraction tasks in China. On the CHN6-CUG dataset, the overall accuracy (OA) and intersection over union (IoU) reach 97.49% and 63.27%, respectively, while on the RDCME dataset, OA and IoU reach 98.73% and 84.97%, respectively. These research results hold significant implications for road traffic, humanitarian rescue, and environmental monitoring, particularly in the context of the Chinese region.

show abstract

Section: Transformer-based Methods For Road Extractionmentioning

confidence: 99%

Global–Local Information Fusion Network for Road Extraction: Bridging the Gap in Accurate Road Segmentation in China

Wang,

Cai,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Scene text detection [129] Complex background Based on a few representative features GANsformer [130] Complex background Combining GAN and transformer Hyneter [131] Complex background HNB+DS TPH-YOLO [132] Complex background Transformer prediction head RODFormer [133] Boundary-arbitrary discontinuity A spatial-FFN feedforward network TransConvNet [134] Boundary-arbitrary discontinuity Combines CNN and self-attention AO2-DETR [135] Boundary-arbitrary discontinuity Generates explicit orientation suggestions O2DETR [136] Boundary-arbitrary discontinuity Apply Transformer to locate objects EFNet [137] Unreliable bounding boxes FCF+RCF TRD [138] Inadequate expression Aggregate multiple scales of features LPSW [139] Inadequate expression Combining transformers and CNNs TransMIN [140] Inadequate expression LGFI+CVFI ViT-YOLO [141] Inadequate expression MHSA-Darknet+BiFPN…”

Section: Problem Solved Optimization Strategiesmentioning

confidence: 99%

“…Additionally, the Swin transformer is enhanced by combining the advantages of transformers and CNNs, resulting in a locally sensing Swin transformer [139] to improve the detection accuracy of small-scale targets. For local-global feature interaction (LGFI), a transformer-guided multi-interaction network [140] (TransMIN) is proposed to learn complementary features using convolution and transformers in the residual blocks in the backbone network. Cross-view feature interaction (CVFI) is also implemented by transformers in the FPN pyramid layer to capture the correlation between reference features and pyramid features.…”

Section: Problem Solved Optimization Strategiesmentioning

confidence: 99%

A Survey of Small Object Detection Based on Deep Learning in Aerial Images

Wang

Chen

2023

Preprint

View full text Add to dashboard Cite

Small object detection poses a formidable challenge in the field of computer vision, particularly when it comes to analyzing aerial remote sensing images. Despite the rapid development of deep learning and significant progress in detection techniques in natural scenes, the migration of these algorithms to aerial images has not met expectations. This is primarily due to limitations in imaging acquisition conditions, including small target size, viewpoint specificity, background complexity, as well as scale and orientation diversity. Although the increasing application of deep learning-based algorithms to overcome these problems, few studies have summarized the optimization of different deep learning strategies used for small target detection in aerial images. Therefore, this paper aims to explore the application of deep learning methods for small object detection in aerial images. The primary challenges in small object detection in aerial images will be summarized. Next, a meticulous analysis and categorization of the prevailing deep learning optimization strategies employed to surmount the challenges encountered in aerial image detection is undertaken. Following that, we provide a comprehensive presentation of the object detection datasets utilized in aerial remote sensing images, along with the evaluation metrics employed. Additionally, we furnish experimental data pertaining to the currently proposed detection algorithms. Finally, the advantages and disadvantages of various optimization strategies and potential development trends are discussed. Hopefully, it can provide a reference for researchers in this field.

show abstract

Enhancing Object Detection in Remote Sensing Images with GFA and ADS Modules Based on InternAware Model

Zhou,

Zhang

2024

2024 6th International Conference on Robotics and Computer Vision (ICRCV)

View full text Add to dashboard Cite

TransMIN: Transformer-Guided Multi-Interaction Network for Remote Sensing Object Detection

Cited by 8 publications

References 33 publications

Global–Local Information Fusion Network for Road Extraction: Bridging the Gap in Accurate Road Segmentation in China

Global–Local Information Fusion Network for Road Extraction: Bridging the Gap in Accurate Road Segmentation in China

A Survey of Small Object Detection Based on Deep Learning in Aerial Images

Enhancing Object Detection in Remote Sensing Images with GFA and ADS Modules Based on InternAware Model

Contact Info

Product

Resources

About