arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.08311cs.CV
收藏

学习适应跨领域的类特定特征以进行语义分割

Learning to adapt class-specific features across domains for semantic segmentation

Computer Vision Center, Universitat Autònoma de Barcelona(巴塞罗那自治大学计算机视觉中心);McGill University(麦吉尔大学)

Mikel Menta, Adriana Romero, Joost van de Weijer

摘要:

无监督领域自适应的最新进展已经表明对抗训练在跨领域适应特征方面的有效性,赋予神经网络在目标领域上进行测试的能力,而无需在该领域中进行任何训练注释。现有的大多数领域自适应模型依赖于图像翻译网络,其中通常包含大量的特定于领域的参数。此外,特征自适应步骤通常在粗略的级别上全局发生,阻碍了其对诸如语义分割之类的任务的适用性,其中细节对于提供清晰的结果至关重要。在这篇论文中,我们提出了一个新的架构,它学习适应跨域的功能,考虑到每类信息。为此,我们设计了一个有条件的逐像素网络,其输出取决于分割掩码。此外,随着图像翻译的最新进展,我们采用了最近推出的StarGAN架构作为图像翻译骨干,因为它能够通过单个生成器网络跨多个域执行翻译。分割任务的初步结果旨在评估所提出的方法的有效性,突出了模型的潜力,提高了强基线和替代设计。

英文摘要:

Recent advances in unsupervised domain adaptation have shown the effectiveness of adversarial training to adapt features across domains, endowing neural networks with the capability of being tested on a target domain without requiring any training annotations in this domain. The great majority of existing domain adaptation models rely on image translation networks, which often contain a huge amount of domain-specific parameters. Additionally, the feature adaptation step often happens globally, at a coarse level, hindering its applicability to tasks such as semantic segmentation, where details are of crucial importance to provide sharp results. In this thesis, we present a novel architecture, which learns to adapt features across domains by taking into account per class information. To that aim, we design a conditional pixel-wise discriminator network, whose output is conditioned on the segmentation masks. Moreover, following recent advances in image translation, we adopt the recently introduced StarGAN architecture as image translation backbone, since it is able to perform translations across multiple domains by means of a single generator network. Preliminary results on a segmentation task designed to assess the effectiveness of the proposed approach highlight the potential of the model, improving upon strong baselines and alternative designs.

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。

↑