Single annotated pixel based weakly supervised semantic segmentation under driving scenes

Li, Xi; Ma, Huimin; Sangbong, Yi; Chen, Yanxian; Ma, Hongbing

doi:10.1016/j.patcog.2021.107979

Cited by 6 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, we may extend the segmentation model to other domains like brain MRIs, lung CT scans, etc. Also, we might incorporate semi-supervision for the segmentation, similar to [28] to extend the models to unlabelled datasets.…”

Section: Discussionmentioning

confidence: 99%

MFSNet: A Multi Focus Segmentation Network for Skin Lesion Segmentation

Basak,

Kundu,

Sarkar

2022

Preprint

View full text Add to dashboard Cite

Segmentation is essential for medical image analysis to identify and localize diseases, monitor morphological changes, and extract discriminative features for further diagnosis. Skin cancer is one of the most common types of cancer globally, and its early diagnosis is pivotal for the complete elimination of malignant tumors from the body. This research develops an Artificial Intelligence (AI) framework for supervised skin lesion segmentation employing the deep learning approach. The proposed framework, called MFSNet (Multi-Focus Segmentation Network), uses differently scaled feature maps for computing the final segmentation mask using raw input RGB images of skin lesions. In doing so, initially, the images are preprocessed to remove unwanted artifacts and noises. The MFSNet employs the Res2Net backbone, a recently proposed convolutional neural network (CNN), for obtaining deep features used in a Parallel Partial Decoder (PPD) module to get a global map of the segmentation mask. In different stages of the network, convolution features and multi-scale maps are used in two boundary attention (BA) modules and two reverse attention (RA) modules to generate the final segmentation output. MFSNet, when evaluated on three publicly available datasets: P H 2 , ISIC 2017, and HAM10000, outperforms state-of-the-art methods, justifying the reliability of the framework. The relevant codes for the proposed approach are accessible at

show abstract

Section: Discussionmentioning

confidence: 99%