Deep Active Contours
This work addresses interactive segmentation for users needing efficient boundary extraction, but it is incremental as it builds on existing active contour methods.
The paper tackles interactive boundary extraction by combining a deep patch-based representation with an active contour framework, resulting in an efficient method that can be trained on small graphics cards and is evaluated on medical and non-medical datasets like STACOM and PASCAL VOC 2012.
We propose a method for interactive boundary extraction which combines a deep, patch-based representation with an active contour framework. We train a class-specific convolutional neural network which predicts a vector pointing from the respective point on the evolving contour towards the closest point on the boundary of the object of interest. These predictions form a vector field which is then used for evolving the contour by the Sobolev active contour framework proposed by Sundaramoorthi et al. The resulting interactive segmentation method is very efficient in terms of required computational resources and can even be trained on comparatively small graphics cards. We evaluate the potential of the proposed method on both medical and non-medical challenge data sets, such as the STACOM data set and the PASCAL VOC 2012 data set.