Automatic Image Labelling at Pixel Level
This addresses the labor-intensive bottleneck in semantic image segmentation for computer vision researchers and practitioners, though it is incremental as it builds on existing weakly-supervised techniques.
The paper tackles the problem of generating pixel-level image labels without manual labor by proposing an iterative learning approach using a Guided Filter Network, achieving results comparable to manual labels and outperforming most weakly-supervised methods.
The performance of deep networks for semantic image segmentation largely depends on the availability of large-scale training images which are labelled at the pixel level. Typically, such pixel-level image labellings are obtained manually by a labour-intensive process. To alleviate the burden of manual image labelling, we propose an interesting learning approach to generate pixel-level image labellings automatically. A Guided Filter Network (GFN) is first developed to learn the segmentation knowledge from a source domain, and such GFN then transfers such segmentation knowledge to generate coarse object masks in the target domain. Such coarse object masks are treated as pseudo labels and they are further integrated to optimize/refine the GFN iteratively in the target domain. Our experiments on six image sets have demonstrated that our proposed approach can generate fine-grained object masks (i.e., pixel-level object labellings), whose quality is very comparable to the manually-labelled ones. Our proposed approach can also achieve better performance on semantic image segmentation than most existing weakly-supervised approaches.