论文标题
F-BRS：重新思考互动分割的重新传播改进
f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation
论文作者
论文摘要
深度神经网络已成为交互分割的主流方法。正如我们在实验中显示的那样，对于某些图像，训练有素的网络仅需单击几下即可提供准确的分割结果，对于某些未知对象，即使有大量的用户输入，也无法获得令人满意的结果。最近提出的反向传播改进（BRS）方案引入了交互式分割的优化问题，在硬案例中导致性能明显更好。同时，BRS需要多次向前和向后通过深层网络，与其他方法相比，每次点击的计算预算大大增加。我们提出了F-BRS（功能反向传播改进方案），该F-BR在辅助变量而不是网络输入方面解决了优化问题，并且需要仅在网络的一小部分中向前和向后传播。与原始BRS相比，有关GrabCut，Berkeley，Davis和SBD数据集的实验设置了新的最新时间。代码和训练有素的模型可在https://github.com/saic-vul/fbrs_interactive_sementation上找到。
Deep neural networks have become a mainstream approach to interactive segmentation. As we show in our experiments, while for some images a trained network provides accurate segmentation result with just a few clicks, for some unknown objects it cannot achieve satisfactory result even with a large amount of user input. Recently proposed backpropagating refinement (BRS) scheme introduces an optimization problem for interactive segmentation that results in significantly better performance for the hard cases. At the same time, BRS requires running forward and backward pass through a deep network several times that leads to significantly increased computational budget per click compared to other methods. We propose f-BRS (feature backpropagating refinement scheme) that solves an optimization problem with respect to auxiliary variables instead of the network inputs, and requires running forward and backward pass just for a small part of a network. Experiments on GrabCut, Berkeley, DAVIS and SBD datasets set new state-of-the-art at an order of magnitude lower time per click compared to original BRS. The code and trained models are available at https://github.com/saic-vul/fbrs_interactive_segmentation .
