Adaptive Spatial Tokenization Transformer for Salient Object Detection in Optical Remote Sensing Images

Gao, Lina; Liu, Bing; Fu, Ping; Xu, Mingzhu

doi:10.1109/tgrs.2023.3242987

Cited by 20 publications

(13 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1) Loss ablation: The hyperparameter γ is incorporated into the coarse prediction branch, specifically subitem L Dice , of the overall loss function (L). In contrast to the conventional loss weight parameters in [51], [64], [65], we set γ to be greater than 1, aligning with our initial intention of constructing boundary detection. While mimicking the DFR for edge extraction, we inadvertently detected internal boundaries within objects, which deviated from our expectations.…”

Section: Ablation Studies and Related Discussionmentioning

confidence: 99%

“…The evaluation involves both qualitative and quantitative analyses. These methods can be classified into five traditional NSI-SOD (RRWR [97], HDCT [98], DSG [99], RCRR [100], VST [50]), seven CNN-based NSI-SOD (DSS [60], RADF [101], EGNet [102], PoolNet [103], GateNet [104], SUCA [105], PA-KRN [106]), three traditional ORSI-SOD (VOS [26], CMC [40], SMFF [39]), and eleven CNN-based ORSI-SOD (LVNet [16], DAFNet [17], EMFINet [64], ERPNet [47], ACCoNet [44], MSCNet [107], SARNet [108], CorrNet [109], FSMINet [110], MJRBM [65], ASTT [51]). Furthermore, among the aforementioned comparative models, we select eleven representative models for further evaluation on the ORSI-4199 dataset to assess their robust generalization.…”

Section: B Comparison With Sota Methodsmentioning

confidence: 99%

“…VST [50] was a pioneer in introducing the transformer to the SOD, replacing conventional CNN models with self-attention mechanisms to explore global information. Subsequently, ASTT [51] designed the adaptive spatial tokenization module (ASTM) to mitigate the impact of optical image features on SOD and also employed the transformer to explore global information. These works have demonstrated the necessity of replacing CNN with transformer architectures to explore global information in the ORSI-SOD.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive Dual-Stream Sparse Transformer Network for Salient Object Detection in Optical Remote Sensing Images

Zhao,

Jia,

et al. 2024

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

View full text Add to dashboard Cite

Excellent performance has been demonstrated by convolutional neural network (CNN) in salient object detection for optical remote sensing images (ORSI-SOD). However, the limitations of CNN's feature extraction using sliding window approach hinder the capture of global representations. Therefore, an end-to-end detection model, known as adaptive dual-stream sparse transformer network (ADSTNet), has been proposed for ORSI-SOD and is assisted by the vision transformer. It effectively addresses the compensation issue of global and local information in ORSI-SOD. In particular, an adaptive interaction encoder has been devised, amalgamating the multi-scale sparse transformer (MST) and the pyramid atrous attention (PAA) to constitute the adaptive dual-stream sparse encoder (ADSE). This encoder collaborates with the CNN to enhance longrange dependency modeling and preserve global information more effectively base on local features. Additionally, a directional feature reconfiguration (DFR) is constructed to extract texture details from multiple directional dimensions. Finally, we propose the adaptive feature cascade decoder (AFCD) that synthesizes content information from the foreground, edges, and background to enhance the representational capacity of the image. Furthermore, a structural loss function, known as the weight compensation mechanism, is introduced to balance the performance of boundary and salmap segmentation losses. The proposed model has been demonstrated to outperform 26 stateof-the-art (SOTA) ORSI-SOD methods across eight evaluation metrics on two standard datasets, as evidenced by extensive experiments. Furthermore, to verify its robustness, the generalization performance of the model on the latest challenging ORSI-4199 dataset is reported. The code and results for this work can be found at https://github.com/JieZzzoo/ADSTNet.

show abstract

Section: Ablation Studies and Related Discussionmentioning

confidence: 99%

Section: B Comparison With Sota Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Dual-Stream Sparse Transformer Network for Salient Object Detection in Optical Remote Sensing Images

Zhao,

Jia,

et al. 2024

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

View full text Add to dashboard Cite

show abstract

“…Over the past decade, convolutional neural network (CNN) has achieved significant advancements in remote sensing, as evidenced in several studies [12][13][14][15]. These advancements have led to markedly improved performance in various areas, including scene classification, object detection, change detection, and image fusion.…”

Section: Introductionmentioning

confidence: 99%

A Spectral–Spatial Context-Boosted Network for Semantic Segmentation of Remote Sensing Images

Li,

Yong,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Semantic segmentation of remote sensing images (RSIs) is pivotal for numerous applications in urban planning, agricultural monitoring, and environmental conservation. However, traditional approaches have primarily emphasized learning within the spatial domain, which frequently leads to less than optimal discrimination of features. Considering the inherent spectral qualities of RSIs, it is essential to bolster these representations by incorporating the spectral context in conjunction with spatial information to improve discriminative capacity. In this paper, we introduce the spectral–spatial context-boosted network (SSCBNet), an innovative network designed to enhance the accuracy semantic segmentation in RSIs. SSCBNet integrates synergetic attention (SYA) layers and cross-fusion modules (CFMs) to harness both spectral and spatial information, addressing the intrinsic complexities of urban and natural landscapes within RSIs. Extensive experiments on the ISPRS Potsdam and LoveDA datasets reveal that SSCBNet surpasses existing state-of-the-art models, achieving remarkable results in F1-scores, overall accuracy (OA), and mean intersection over union (mIoU). Ablation studies confirm the significant contribution of SYA layers and CFMs to the model’s performance, emphasizing the effectiveness of these components in capturing detailed contextual cues.

show abstract

“…In this context, the task of object detection within RSIs plays a crucial role by providing valuable insights for making wellinformed decisions. However, current object detection methods based on deep learning, which rely on complete supervision [1,2,3,4,5,6,7], often depend on a substantial amount of annotated data. This annotation process can be both time-consuming and financially demanding.…”

Section: Introductionmentioning

confidence: 99%

Feature Alignment FPN for Oriented Object Detection in Remote Sensing Images

et al. 2023

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

Annotating remote sensing images (RSIs) presents a notable challenge due to its labor-intensive nature. Semisupervised object detection (SSOD) methods tackle this issue by generating pseudo-labels for the unlabeled data, assuming that all classes found in the unlabeled dataset are also represented in the labeled data. However, real-world situations introduce the possibility of out-of-distribution (OOD) samples being mixed with in-distribution (ID) samples within the unlabeled dataset. In this paper, we delve into techniques for conducting SSOD directly on uncurated unlabeled data, which is termed Open-Set Semi-Supervised Object Detection (OSSOD). Our approach commences by employing labeled in-distribution data to dynamically construct a class-wise feature bank (CFB) that captures features specific to each class. Subsequently, we compare the features of predicted object bounding boxes with the corresponding entries in the CFB to calculate OOD scores. We design an adaptive threshold based on the statistical properties of the CFB, allowing us to filter out OOD samples effectively. The effectiveness of our proposed method is substantiated through extensive experiments on two widely used remote sensing object detection datasets: DIOR and DOTA. These experiments showcase the superior performance and efficacy of our approach for OSSOD on RSIs.

show abstract

Adaptive Spatial Tokenization Transformer for Salient Object Detection in Optical Remote Sensing Images

Cited by 20 publications

References 74 publications

Adaptive Dual-Stream Sparse Transformer Network for Salient Object Detection in Optical Remote Sensing Images

Adaptive Dual-Stream Sparse Transformer Network for Salient Object Detection in Optical Remote Sensing Images

A Spectral–Spatial Context-Boosted Network for Semantic Segmentation of Remote Sensing Images

Feature Alignment FPN for Oriented Object Detection in Remote Sensing Images

Contact Info

Product

Resources

About