Representation-Enhanced Status Replay Network for Multisource Remote-Sensing Image Classification

Wang, Junjie; Li, Wei; Wang, Yinjian; Tao, Ran; Du, Qian

doi:10.1109/tnnls.2023.3286422

Cited by 60 publications

(11 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For remote sensing images, Multi‐stage Self‐Guided Separation Network (MGSNet) [14] used different feature extraction branches to extract the target, background, and overall features simultaneously. Representation‐enhanced Status Replay Network (RSRNet) [15] proposed a dual‐modal and semantic enhancement approach to enhance feature diversity, and adopts a cross‐modal interactive fusion approach to obtain complementary information from multiple sources. Structural Optimization transmission Network (SOT‐Net) [16] adopted a cross‐attention mechanism and symmetric bimodal propagation module to solve the problem of feature imbalance and redundant interference from multiple sources.…”

Section: Related Workmentioning

confidence: 99%

Cross‐modal knowledge learning with scene text for fine‐grained image classification

Xiong,

Mao,

Wang

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

Scene text in natural images carries additional semantic information to aid in image classification. Existing methods lack full consideration of the deep understanding of the text and the visual text relationship, which results in the difficult to judge the semantic accuracy and the relevance of the visual text. This paper proposes image classification based on Cross modal Knowledge Learning of Scene Text (CKLST) method. CKLST consists of three stages: cross‐modal scene text recognition, text semantic enhancement, and visual‐text feature alignment. In the first stage, multi‐attention is used to extract features layer by layer, and a self‐mask‐based iterative correction strategy is utilized to improve the scene text recognition accuracy. In the second stage, knowledge features are extracted using external knowledge and are fused with text features to enhance text semantic information. In the third stage, CKLST realizes visual‐text feature alignment across attention mechanisms with a similarity matrix, thus the correlation between images and text can be captured to improve the accuracy of the image classification tasks. On Con‐Text dataset, Crowd Activity dataset, Drink Bottle dataset, and Synth Text dataset, CKLST can perform significantly better than other baselines on fine‐grained image classification, with improvements of 3.54%, 5.37%, 3.28%, and 2.81% over the best baseline in mAP, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Cross‐modal knowledge learning with scene text for fine‐grained image classification

Xiong,

Mao,

Wang

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…J. Wang et al proposed some advanced research achievements, such as the MultiStage Self-Guided Sep-aration Network and Representation-Enhanced Status Replay Network [7,8]. M. Zhang et al proposed SOT-NET [9].…”

Section: Introductionmentioning

confidence: 99%

YOLOv5s maritime distress target detection method based on swin transformer

Liu,

Qi,

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

In recent years, the task of maritime emergency rescue has increased, while the cost of time for traditional methods of search and rescue is pretty long with poor effect subject to the constraints of the complex circumstances around the sea, the effective conditions, and the support capability. This paper applies deep learning and proposes a YOLOv5s‐SwinDS algorithm for target detection in distress at sea. Firstly, the backbone network of the YOLOv5s algorithm is replaced by swin transformer, and a multi‐level feature fusion module is introduced to enhance the feature expression ability for maritime targets. Secondly, deformable convolutional networks v2 (DCNv2) is used instead of traditional convolution to improve the recognition capability for irregular targets when the neck network features are output. Finally, the CIoU loss function is replaced with SIoU to reduce the redundant box effectively while accelerating the convergence and regression of the predicted box. Experimenting on the publicly dataset SeaDronesSee, the , , and of YOLOv5s‐SwinDS model are 87.9%, 75.8%, 79.1% and 42.9%, respectively, which get higher results than the original YOLOv5s model, the YOLOv7 series of models, and the YOLOv8 series of models. The experiments verifies that the algorithm has good performance in detecting maritime distress targets.

show abstract

“…Meanwhile, some cutting-edge research has combined multisource remote-sensing data for land cover classification. Li et al [29], [30] proposed a spatial logic aggregation network with morphological transformation for tree species classification. Additionally, they introduced a Representationenhanced Status Replay Network (RSRNet), which includes modal and semantic augmentation enhancement to enhance the transferability and discreteness of feature representation, reduces the impact of representation bias in the feature extractor, and alleviates the bias of the classifier while maintaining the stability of the decision boundary.…”

Section: Introductionmentioning

confidence: 99%

“…The SRS was built to regulate the learning and optimization of the classifier. The RSRNet has demonstrated superiority in multisource remote-sensing image classification [29], [30].…”

Section: Introductionmentioning

confidence: 99%

MAST: An Earthquake-Triggered Landslides Extraction Method Combining Morphological Analysis Edge Recognition With Swin-Transformer Deep Learning Model

Huang,

Zhang,

et al. 2024

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

View full text Add to dashboard Cite

Earthquake-triggered landslides (ETLs) are characterized by their extensive occurrences, having wide distributions. The conventional human-computer interaction extraction method is often time-consuming and labor-intensive, failing to meet the demands of disaster emergency response. There is a pressing need for a swift detection of ETLs. In this study, we introduce an ETLs extraction method (MAST) combining morphological analysis edge recognition with a Swin-Transformer (SWT) deep learning model, which is specifically designed for landslide extraction. The MAST model adopts a hierarchical construction approach akin to convolution neural networks, aiding in tasks such as target detection and semantic segmentation. To enhance the accuracy of landslide Manuscript

show abstract

Representation-Enhanced Status Replay Network for Multisource Remote-Sensing Image Classification

Cited by 60 publications

References 45 publications

Cross‐modal knowledge learning with scene text for fine‐grained image classification

Cross‐modal knowledge learning with scene text for fine‐grained image classification

YOLOv5s maritime distress target detection method based on swin transformer

MAST: An Earthquake-Triggered Landslides Extraction Method Combining Morphological Analysis Edge Recognition With Swin-Transformer Deep Learning Model

Contact Info

Product

Resources

About