Rethinking Unsupervised Neural Superpixel Segmentation
This work addresses superpixel segmentation for computer vision applications, but it appears incremental as it builds on existing unsupervised CNN methods.
The paper tackled the problem of unsupervised neural superpixel segmentation by proposing three key elements to improve efficacy, resulting in evidence of significance on the BSDS500 dataset both qualitatively and quantitatively.
Recently, the concept of unsupervised learning for superpixel segmentation via CNNs has been studied. Essentially, such methods generate superpixels by convolutional neural network (CNN) employed on a single image, and such CNNs are trained without any labels or further information. Thus, such approach relies on the incorporation of priors, typically by designing an objective function that guides the solution towards a meaningful superpixel segmentation. In this paper we propose three key elements to improve the efficacy of such networks: (i) the similarity of the \emph{soft} superpixelated image compared to the input image, (ii) the enhancement and consideration of object edges and boundaries and (iii) a modified architecture based on atrous convolution, which allow for a wider field of view, functioning as a multi-scale component in our network. By experimenting with the BSDS500 dataset, we find evidence to the significance of our proposal, both qualitatively and quantitatively.