Attention Deeplabv3+: Multi-level Context Attention Mechanism for Skin Lesion Segmentation

Azad, Reza; Asadi-Aghbolaghi, Maryam; Fathy, Mahmood; Escalera, Sérgio

doi:10.1007/978-3-030-66415-2_16

Cited by 79 publications

(45 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It can be seen that there have been better performances for different models compared with ISIC 2018, and our weakly supervised segmentation method also achieved a competitive performance with other fully supervised segmentation models. From these related works, performed for skin lesion segmentation, we can see that our method achieves a competitive performance compared with the classic lesion segmenting methods-Wu's method [84], HRFB [88] and Att-Deeplab V3+ [79]. In addition, our method is different to these related methods.…”

Section: Isicmentioning

confidence: 85%

“…HRFB [88] provides high-resolution feature mapping to preserve spatial details. Att-Deeplab V3+ [79] introduces two levels of attention mechanism based on deeplab V3+ to capture the relationships between a group of features. We introduce the CBAM module into the FPN (Feature Pyramid Networks) network to form an attention FPN, so as to improve the network's perception of multi-scale images.…”

Section: Isicmentioning

confidence: 99%

See 1 more Smart Citation

Lesion Segmentation Framework Based on Convolutional Neural Networks with Dual Attention Mechanism

Xie

Zhang

Jiang³

et al. 2021

Electronics

View full text Add to dashboard Cite

Computational intelligence has been widely used in medical information processing. The deep learning methods, especially, have many successful applications in medical image analysis. In this paper, we proposed an end-to-end medical lesion segmentation framework based on convolutional neural networks with a dual attention mechanism, which integrates both fully and weakly supervised segmentation. The weakly supervised segmentation module achieves accurate lesion segmentation by using bounding-box labels of lesion areas, which solves the problem of the high cost of pixel-level labels with lesions in the medical images. In addition, a dual attention mechanism is introduced to enhance the network’s ability for visual feature learning. The dual attention mechanism (channel and spatial attention) can help the network pay attention to feature extraction from important regions. Compared with the current mainstream method of weakly supervised segmentation using pseudo labels, it can greatly reduce the gaps between ground-truth labels and pseudo labels. The final experimental results show that our proposed framework achieved more competitive performances on oral lesion dataset, and our framework further extended to dermatological lesion segmentation.

show abstract

Section: Isicmentioning

confidence: 85%

Section: Isicmentioning

confidence: 99%

Lesion Segmentation Framework Based on Convolutional Neural Networks with Dual Attention Mechanism

Xie

Zhang

Jiang³

et al. 2021

Electronics

View full text Add to dashboard Cite

show abstract

“…To mitigate the performance drop of segmentation DNNs on boundary regions of spike in unseen data, the neural network should have a broad feature map to accommodate the fine texture in the edge as well as the central part of a spike. In recent studies, to make DNNs more robust, one improvement was the introduction of weighting each channel (attention) in several layers to emphasize more on the informative channel and scale relevant feature of the object [34].…”

Section: Discussionmentioning

confidence: 99%

Towards Automated Analysis of Grain Spikes in Greenhouse Images Using Neural Network Approaches: A Comparative Investigation of Six Methods

Ullah

Henke

Narisetti

et al. 2021

Sensors

View full text Add to dashboard Cite

Automated analysis of small and optically variable plant organs, such as grain spikes, is highly demanded in quantitative plant science and breeding. Previous works primarily focused on the detection of prominently visible spikes emerging on the top of the grain plants growing in field conditions. However, accurate and automated analysis of all fully and partially visible spikes in greenhouse images renders a more challenging task, which was rarely addressed in the past. A particular difficulty for image analysis is represented by leaf-covered, occluded but also matured spikes of bushy crop cultivars that can hardly be differentiated from the remaining plant biomass. To address the challenge of automated analysis of arbitrary spike phenotypes in different grain crops and optical setups, here, we performed a comparative investigation of six neural network methods for pattern detection and segmentation in RGB images, including five deep and one shallow neural network. Our experimental results demonstrate that advanced deep learning methods show superior performance, achieving over 90% accuracy by detection and segmentation of spikes in wheat, barley and rye images. However, spike detection in new crop phenotypes can be performed more accurately than segmentation. Furthermore, the detection and segmentation of matured, partially visible and occluded spikes, for which phenotypes substantially deviate from the training set of regular spikes, still represent a challenge to neural network models trained on a limited set of a few hundreds of manually labeled ground truth images. Limitations and further potential improvements of the presented algorithmic frameworks for spike image analysis are discussed. Besides theoretical and experimental investigations, we provide a GUI-based tool (SpikeApp), which shows the application of pre-trained neural networks to fully automate spike detection, segmentation and phenotyping in images of greenhouse-grown plants.

show abstract

“…In addition, the atrous convolution can greatly reduce the complexity and obtain similar (or better) DeepLabV3+ is a semantic segmentation neural network designed by Liang Chieh Chen et al [21] in 2018 and is based on DeepLabV3. DeepLabV3+ is now widely used in various complex scenes for target segmentation, such as for skin lesions, road potholes, and weeds [22][23][24]. The network is composed of two parts: the encoder and the decoder, as shown in Figure 5.…”

Section: Deeplabv3+ Networkmentioning

confidence: 99%

Segmentation of Overlapping Grape Clusters Based on the Depth Region Growing Method

2021

View full text Add to dashboard Cite

Accurately extracting the grape cluster at the front of overlapping grape clusters is the primary problem of the grape-harvesting robot. To solve the difficult problem of identifying and segmenting the overlapping grape clusters in the cultivation environment of a trellis, a simple method based on the deep learning network and the idea of region growing is proposed. Firstly, the region of grape in an RGB image was obtained by the finely trained DeepLabV3+ model. The idea of transfer learning was adopted when training the network with a limited number of training sets. Then, the corresponding region of the grape in the depth image captured by RealSense D435 was processed by the proposed depth region growing algorithm (DRG) to extract the front cluster. The depth region growing method uses the depth value instead of gray value to achieve clustering. Finally, it fils the holes in the clustered region of interest, extracts the contours, and maps the obtained contours to the RGB image. The images captured by RealSense D435 in a natural trellis environment were adopted to evaluate the performance of the proposed method. The experimental results showed that the recall and precision of the proposed method were 89.2% and 87.5%, respectively. The demonstrated performance indicated that the proposed method could satisfy the requirements of practical application for robotic grape harvesting.

show abstract

Attention Deeplabv3+: Multi-level Context Attention Mechanism for Skin Lesion Segmentation

Cited by 79 publications

References 27 publications

Lesion Segmentation Framework Based on Convolutional Neural Networks with Dual Attention Mechanism

Lesion Segmentation Framework Based on Convolutional Neural Networks with Dual Attention Mechanism

Towards Automated Analysis of Grain Spikes in Greenhouse Images Using Neural Network Approaches: A Comparative Investigation of Six Methods

Segmentation of Overlapping Grape Clusters Based on the Depth Region Growing Method

Contact Info

Product

Resources

About