SideInfNet: A Deep Neural Network for Semi-Automatic Semantic Segmentation with Side Information
This work addresses the need for accurate and user-guided segmentation in domains like medical imaging, where fully-automatic methods are risky, though it appears incremental as it builds on existing semi-automatic approaches.
The paper tackled the problem of high-cost tasks like medical segmentation by proposing SideInfNet, a deep neural network that integrates image features with user-provided side information for semi-automatic semantic segmentation, achieving verified superiority in experiments on three benchmark datasets.
Fully-automatic execution is the ultimate goal for many Computer Vision applications. However, this objective is not always realistic in tasks associated with high failure costs, such as medical applications. For these tasks, semi-automatic methods allowing minimal effort from users to guide computer algorithms are often preferred due to desirable accuracy and performance. Inspired by the practicality and applicability of the semi-automatic approach, this paper proposes a novel deep neural network architecture, namely SideInfNet that effectively integrates features learnt from images with side information extracted from user annotations. To evaluate our method, we applied the proposed network to three semantic segmentation tasks and conducted extensive experiments on benchmark datasets. Experimental results and comparison with prior work have verified the superiority of our model, suggesting the generality and effectiveness of the model in semi-automatic semantic segmentation.