Deep Variational Instance Segmentation
This addresses the problem of instance segmentation in computer vision by introducing a more direct and efficient method, though it appears incremental as it builds on existing variational segmentation approaches.
The paper tackles instance segmentation by proposing a novel algorithm that uses a fully convolutional network to predict instance labels through a variational relaxation of the segmentation problem, achieving efficient performance on datasets like PASCAL VOC 2012, SBD, and MSCOCO 2017.
Instance Segmentation, which seeks to obtain both class and instance labels for each pixel in the input image, is a challenging task in computer vision. State-of-the-art algorithms often employ two separate stages, the first one generating object proposals and the second one recognizing and refining the boundaries. Further, proposals are usually based on detectors such as faster R-CNN which search for boxes in the entire image exhaustively. In this paper, we propose a novel algorithm that directly utilizes a fully convolutional network (FCN) to predict instance labels. Specifically, we propose a variational relaxation of instance segmentation as minimizing an optimization functional for a piecewise-constant segmentation problem, which can be used to train an FCN end-to-end. It extends the classical Mumford-Shah variational segmentation problem to be able to handle permutation-invariant labels in the ground truth of instance segmentation. Experiments on PASCAL VOC 2012, Semantic Boundaries dataset(SBD), and the MSCOCO 2017 dataset show that the proposed approach efficiently tackle the instance segmentation task. The source code and trained models will be released with the paper.