Improving Fast Segmentation With Teacher-student Learning
This work addresses the trade-off between speed and accuracy in segmentation models for practical applications, but it is incremental as it builds on existing teacher-student methods.
The paper tackles the problem of slow inference speed in segmentation neural networks by proposing a teacher-student learning framework that transfers knowledge from heavy, accurate models to fast ones, improving accuracy without extra computational cost, with experiments on datasets like Pascal Context showing significant performance boosts.
Recently, segmentation neural networks have been significantly improved by demonstrating very promising accuracies on public benchmarks. However, these models are very heavy and generally suffer from low inference speed, which limits their application scenarios in practice. Meanwhile, existing fast segmentation models usually fail to obtain satisfactory segmentation accuracies on public benchmarks. In this paper, we propose a teacher-student learning framework that transfers the knowledge gained by a heavy and better performed segmentation network (i.e. teacher) to guide the learning of fast segmentation networks (i.e. student). Specifically, both zero-order and first-order knowledge depicted in the fine annotated images and unlabeled auxiliary data are transferred to regularize our student learning. The proposed method can improve existing fast segmentation models without incurring extra computational overhead, so it can still process images with the same fast speed. Extensive experiments on the Pascal Context, Cityscape and VOC 2012 datasets demonstrate that the proposed teacher-student learning framework is able to significantly boost the performance of student network.