Deep Interactive Object Selection
This work addresses the need for more efficient interactive object selection in applications like image editing, though it is incremental as it builds on prior methods with deep learning enhancements.
The paper tackles the problem of reducing user interactions in interactive object selection by introducing a deep learning algorithm that transforms user clicks into distance maps and fine-tunes Fully Convolutional Networks, achieving superior performance with just a few clicks compared to existing approaches.
Interactive object selection is a very important research problem and has many applications. Previous algorithms require substantial user interactions to estimate the foreground and background distributions. In this paper, we present a novel deep learning based algorithm which has a much better understanding of objectness and thus can reduce user interactions to just a few clicks. Our algorithm transforms user provided positive and negative clicks into two Euclidean distance maps which are then concatenated with the RGB channels of images to compose (image, user interactions) pairs. We generate many of such pairs by combining several random sampling strategies to model user click patterns and use them to fine tune deep Fully Convolutional Networks (FCNs). Finally the output probability maps of our FCN 8s model is integrated with graph cut optimization to refine the boundary segments. Our model is trained on the PASCAL segmentation dataset and evaluated on other datasets with different object classes. Experimental results on both seen and unseen objects clearly demonstrate that our algorithm has a good generalization ability and is superior to all existing interactive object selection approaches.