Denoised Non-Local Neural Network for Semantic Segmentation

Song, Qi; Li, Jie; Guo, Hao; Huang, Rui

doi:10.1109/tnnls.2022.3214216

Cited by 7 publications

(3 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the local detail encoder can extract detailed feature information from an image, its field of perception is still limited, and it cannot extract information from the entire image at once. Even though different convolutions can be cascaded to expand the field, the effective field occupies only a small fraction of the theoretical field, making the direct extraction of long-distance-dependent information impossible [38]. The feature vectors extracted by transformers usually contain more global contextual information [39].…”

Section: Lightweight Transformer Encodermentioning

confidence: 99%

LCANet: A Lightweight Context-Aware Network for Bladder Tumor Segmentation in MRI Images

Wang,

Li,

2023

Mathematics

View full text Add to dashboard Cite

Accurate segmentation of the lesion area from MRI images is essential for diagnosing bladder cancer. However, the precise segmentation of bladder tumors remains a massive challenge due to their similar intensity distributions, various tumor morphologies, and blurred boundaries. While some seminal studies, such as those using CNNs combined with transformer segmentation methods, have made significant progress, (1) how to reduce the computational complexity of the self-attention mechanism in the transformer while maintaining performance and (2) how to build a better global feature fusion process to improve segmentation performance still require further exploration. Considering the complexity of bladder MRI images, we developed a lightweight context-aware network (LCANet) to automatically segment bladder lesions from MRI images. Specifically, the local detail encoder generates local-level details of the lesion, the lightweight transformer encoder models the global-level features with different resolutions, the pyramid scene parsing module extracts high-level and multiscale semantic features, and the decoder provides high-resolution segmentation results by fusing local-level details with global-level cues at the channel level. A series of empirical studies on T2-weighted MRI images from 86 patients show that LCANet achieves an overall Jaccard index of 89.39%, a Dice similarity coefficient of 94.08%, and a Class pixel accuracy of 94.10%. These advantages show that our method is an efficient tool that can assist in reducing the heavy workload of radiologists.

show abstract

Section: Lightweight Transformer Encodermentioning

confidence: 99%

LCANet: A Lightweight Context-Aware Network for Bladder Tumor Segmentation in MRI Images

Wang,

Li,

2023

Mathematics

View full text Add to dashboard Cite

show abstract

“…Yang [40] designed a deep convolutional neural network incorporating a fuzzy attention mechanism, effectively improving medical image segmentation accuracy. Nan [41] proposed an airway segmentation method, which enhances the continuity of the segmentation utilizing a fuzzy attention neural network and a combined loss function. Xiao [42], in a real driving scenario,…”

Section: ⅰ Introductionmentioning

confidence: 99%

Fuzzy EfficientDet: An Approach for Precise Detection of Larch Infestation Severity in UAV Imagery Under Dynamic Environmental Conditions

Yang,

Li,

et al. 2024

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

View full text Add to dashboard Cite

In this paper, a novel deep learning framework, fuzzy EfficientDet, is proposed to address the challenge of accurately detecting larch infested by Coleophora laricella pests in UAV imagery, where the key innovation is the incorporation of the fuzzy spatial attention mechanism (FSAM), which can effectively deal with the problem of model uncertainty due to the complexity of environmental transformations and image features. First, this study designs and implements a Global-Local Squeeze-and-Excitation Module, which profoundly integrates global and local feature information, realizes the dynamic adaptation of the importance of feature channels in the EfficientNet, and thus improves the overall feature expression efficiency of the network. Second, this study constructed a dense Bi-FPN architecture, which adds a dense connection structure to the original Bi-FPN to enhance the modeling accuracy for small targets and long-range spatial dependencies. Finally, this study develops the fuzzy spatial attention mechanism (FSAM), which can effectively mitigate the unstable performance of the EfficientDet in the face of image feature fluctuations triggered by changes in lighting conditions and seasonal effects. Experiments demonstrate that the proposed fuzzy EfficientDet model shows superior performance compared to the traditional SSD, Faster R-CNN, YOLO V5, and the unimproved EfficientDet target detection method on the Swedish Forest Agency (2021) dataset, with its mAP as high as 94.29%. This result demonstrates that fuzzy EfficientDet provides an efficient and reliable solution when dealing with the task of target detection in UAV images, especially in dealing with environmental uncertainty and complex feature extraction.

show abstract

“…After obtaining hierarchical features from the encoder, a sequence of decoder structures is proposed. For designing the decoders, the general strategy is to take advantage of multi-level encoded features from the aspects of modeling multi-scale contextual information [22], [31]- [34], [63], mining long-range dependency information [21], [23], [30], [41], [64], [65], or feature refinement [25], [27], [62].…”

Section: Introductionmentioning

confidence: 99%

Multiregion Scale-Aware Network for Building Extraction From High-Resolution Remote Sensing Images

Liu

Zhao

Zhang

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Building extraction aims to segment building pixels from remote sensing images and plays an essential role in many applications, such as city planning and urban dynamic monitoring. Over the past few years, deep learning methods with encoder-decoder architectures have achieved remarkable performance due to their powerful feature representation capability. Nevertheless, due to the varying scales and styles of buildings, conventional deep learning models always suffer from uncertain predictions and cannot accurately distinguish the complete footprints of the building from the complex distribution of ground objects, leading to a large degree of omission and commission. In this paper, we realize the importance of uncertain prediction and propose a novel and straightforward Uncertainty-Aware Network (UANet) to alleviate this problem. Specifically, we first apply a general encoder-decoder network to obtain a building extraction map with relatively high uncertainty. Second, in order to aggregate the useful information in the highest-level features, we design a Prior Information Guide Module to guide the highest-level features in learning the prior information from the conventional extraction map. Third, based on the uncertain extraction map, we introduce an Uncertainty Rank Algorithm to measure the uncertainty level of each pixel belonging to the foreground and the background. We further combine this algorithm with the proposed Uncertainty-Aware Fusion Module to facilitate level-by-level feature refinement and obtain the final refined extraction map with low uncertainty. To verify the performance of our proposed UANet, we conduct extensive experiments on three public building datasets, including the WHU building dataset, the Massachusetts building dataset, and the Inria aerial image dataset. Results demonstrate that the proposed UANet outperforms other state-of-the-art algorithms by a large margin. The source code of the proposed UANet is available at https://github.com/Henryjiepanli/Uncertainty-aware-Network.

show abstract

Denoised Non-Local Neural Network for Semantic Segmentation

Cited by 7 publications

References 64 publications

LCANet: A Lightweight Context-Aware Network for Bladder Tumor Segmentation in MRI Images

LCANet: A Lightweight Context-Aware Network for Bladder Tumor Segmentation in MRI Images

Fuzzy EfficientDet: An Approach for Precise Detection of Larch Infestation Severity in UAV Imagery Under Dynamic Environmental Conditions

Multiregion Scale-Aware Network for Building Extraction From High-Resolution Remote Sensing Images

Contact Info

Product

Resources

About