arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.06394cs.CV
收藏

您只需要几个像素:使用PixelPick进行语义分割

All you need are a few pixels: semantic segmentation with PixelPick

University of Oxford(牛津大学)

Gyungin Shin, Weidi Xie, Samuel Albanie

摘要:

语义分割任务的核心挑战是获得密集像素级注释以监督模型训练的高昂成本。在这项工作中,我们表明,为了实现良好的分割性能,您所需要的只是一些精心选择的像素标签。我们做出了以下贡献:(i)我们研究了新的语义分割设置,其中标签仅在稀疏像素位置提供,并表明深度神经网络可以使用少量这样的标签来获得良好的效果;(ii)我们展示了如何在一个称为PixelPick的主动学习框架内利用这种现象,以从根本上降低标签成本,(iii)我们进行了大量的实验来研究在固定预算、模型预训练、模型容量和在这种低注释制度下拾取像素的采样机制下注释多样性的影响;(iv)我们提供了与具有主动学习的语义分割的现有技术水平的比较,并且在CamVid、Cityscapes和PASCAL VOC 2012基准上展示了具有高达两个数量级的像素注释的可比性能;(v)最后,我们评估了我们的注释管道的效率及其对注释者错误的敏感性,以证明其实用性。

英文摘要:

A central challenge for the task of semantic segmentation is the prohibitive cost of obtaining dense pixel-level annotations to supervise model training. In this work, we show that in order to achieve a good level of segmentation performance, all you need are a few well-chosen pixel labels. We make the following contributions: (i) We investigate the novel semantic segmentation setting in which labels are supplied only at sparse pixel locations, and show that deep neural networks can use a handful of such labels to good effect; (ii) We demonstrate how to exploit this phenomena within an active learning framework, termed PixelPick, to radically reduce labelling cost, and propose an efficient "mouse-free" annotation strategy to implement our approach; (iii) We conduct extensive experiments to study the influence of annotation diversity under a fixed budget, model pretraining, model capacity and the sampling mechanism for picking pixels in this low annotation regime; (iv) We provide comparisons to the existing state of the art in semantic segmentation with active learning, and demonstrate comparable performance with up to two orders of magnitude fewer pixel annotations on the CamVid, Cityscapes and PASCAL VOC 2012 benchmarks; (v) Finally, we evaluate the efficiency of our annotation pipeline and its sensitivity to annotator error to demonstrate its practicality.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑