arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1704.08082cs.CV
收藏

AutoDIAL:自动DomaIn配向层

AutoDIAL: Automatic DomaIn Alignment Layers

Sapienza, Roma(罗马大学);IRI CSIC-UPC, Barcelona(西班牙高等科研理事会-加泰罗尼亚理工大学机器人研究所);Mapillary, Graz(Mapillary公司);FBK, Trento(特伦托布鲁诺·凯斯勒基金会);University of Perugia(佩鲁贾大学)

Fabio Maria Carlucci, Lorenzo Porzi, Barbara Caputo, Elisa Ricci, Samuel Rota Bulò

摘要:

在给定数据库上训练的分类器在对不同设置中获取的数据进行测试时表现不佳。这在领域自适应中通过源和目标领域的分布之间的移位来解释。传统上,将它们对齐的尝试会导致作品通过在目标函数中引入适当的损失项、测量源分布和目标分布之间的差异来减少域转移。在这里,我们采取了不同的路线,建议通过嵌入任何给定的网络特定的域对齐层来对齐学习的表示,旨在将源和目标特征分布与参考分布相匹配。与之前定义先验的工作相反,我们的方法能够自动学习深度网络不同级别所需的特征对齐程度。在无监督环境下,对不同的公共基准进行了彻底的实验,证实了我们方法的强大功能。

英文摘要:

Classifiers trained on given databases perform poorly when tested on data acquired in different settings. This is explained in domain adaptation through a shift among distributions of the source and target domains. Attempts to align them have traditionally resulted in works reducing the domain shift by introducing appropriate loss terms, measuring the discrepancies between source and target distributions, in the objective function. Here we take a different route, proposing to align the learned representations by embedding in any given network specific Domain Alignment Layers, designed to match the source and target feature distributions to a reference one. Opposite to previous works which define a priori in which layers adaptation should be performed, our method is able to automatically learn the degree of feature alignment required at different levels of the deep network. Thorough experiments on different public benchmarks, in the unsupervised setting, confirm the power of our approach.

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。

↑