AdaContour: Adaptive Contour Descriptor with Hierarchical Representation
This work addresses a specific bottleneck in computer vision for shape analysis, offering an incremental improvement over existing contour descriptors.
The paper tackles the problem of representing non-starconvex shapes in contour descriptors, which existing angle-based methods handle poorly due to single global representations, and proposes AdaContour, an adaptive descriptor using multiple local representations to achieve more accurate and robust shape representation, with experiments showing improved performance over other descriptors.
Existing angle-based contour descriptors suffer from lossy representation for non-starconvex shapes. By and large, this is the result of the shape being registered with a single global inner center and a set of radii corresponding to a polar coordinate parameterization. In this paper, we propose AdaContour, an adaptive contour descriptor that uses multiple local representations to desirably characterize complex shapes. After hierarchically encoding object shapes in a training set and constructing a contour matrix of all subdivided regions, we compute a robust low-rank robust subspace and approximate each local contour by linearly combining the shared basis vectors to represent an object. Experiments show that AdaContour is able to represent shapes more accurately and robustly than other descriptors while retaining effectiveness. We validate AdaContour by integrating it into off-the-shelf detectors to enable instance segmentation which demonstrates faithful performance. The code is available at https://github.com/tding1/AdaContour.