Survey of Computer Vision and Machine Learning in Gastrointestinal Endoscopy

Vemuri, Anant S.

doi:10.48550/arxiv.1904.13307

Cited by 1 publication

(2 citation statements)

References 149 publications

(156 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For a given feature mapX∈R C × H × W two transformations are performed separately by parallel convolutional branches with kernel sizes of 3×3 and 5×5 to extract features at different scales. The results from multiple branches (two branches in Figure 2) are then summed element-wise to fuse them, as shown in Equations ( 1), (2), and (3).…”

Section: Efficient Channel Attention Modulementioning

confidence: 99%

“…In recent years, significant breakthroughs have been achieved in image segmentation in computer vision through the establishment of various neural network models in deep learning. Particularly, the successful application of Convolutional Neural Networks (CNN) [2], such as U-Net [3], Seg-Net [4], FCN [5]has been widely adopted in various computer vision tasks. In addition to complete network architectures, attention mechanisms have been extensively applied in the field of image segmentation in recent years [6] [7], Attention mechanisms can operate on different dimensions, including channel dimension and spatial dimension.…”

mentioning

confidence: 99%

See 1 more Smart Citation

PASK-Net: A Hybrid Network for Polyps Image Segmentation

Lv,

Lu,

2024

Preprint

View full text Add to dashboard Cite

Accurate segmentation of polyps is crucial in the field of medical image recognition. Attention mechanisms have been widely applied in medical image segmentation, but attention mechanisms implemented by convolution are limited in capturing multi-scale information due to the constraints of convolution kernel sizes. This linear aggregation method restricts the network's adaptability to various complex situations and has limitations in handling multi-scale information. Therefore, this paper proposes PASK-Net, which performs serial computations in both channel and spatial dimensions. In the channel dimension, a nonlinear approach is introduced to achieve neuron-adaptive receptive field sizes, addressing the problem of fixed convolutional processing range in attention mechanisms that hinders effective acquisition of multi-scale information. Meanwhile, in the spatial dimension, Channel-Prioritized Convolutional Attention (CPCA) is introduced to enhance the network's feature representation capability by aggregating multi-scale information from different-sized convolutional kernel branches, while ensuring computational efficiency. Comparative experiments on the Kvasir dataset demonstrate that, compared to other networks, the PASK module performs well on six evaluation metrics including Dice and IOU, achieving a Dice value of 87.54% and an IOU value of 80.6%, effectively improving the accuracy of polyp segmentation. Results from ablation experiments also validate the effectiveness of the module. The codes are available at https://github.com/LvYamKun/PASK-Net

show abstract

Section: Efficient Channel Attention Modulementioning

confidence: 99%