CVPR 2019 Open Access Repository

Discovering Visual Patterns in Art Collections With Spatially-Consistent Feature Learning Abstract Our goal in this paper is to discover near duplicate patterns in large collections of artworks. This is harder than standard instance mining due to differences in the artistic media (oil, pastel, drawing, etc), and imperfections inherent in the copying process. Our key technical insight is to adapt a standard deep feature to this task by fine-tuning it on the specific art collection using self-supervised learning. More specifically, spatial consistency between neighbouring feature matches is used as supervisory fine-tuning signal. The adapted feature leads to more accurate style invariant matching, and can be used with a standard discovery approach, based on geometric verification, to identify duplicate patterns in the dataset. The approach is evaluated on several different datasets and shows surprisingly good qualitative discovery results. For quantitative evaluation of the method, we ...

1 mentions: @t_Signull
Keywords: cvpr
Date: 2019/06/14 14:17

Referring Tweets

@t_Signull Efrosセンセが著者に入ってるこの論文タイトルだけで面白いとわかる Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning

Related Entries

Read more 教師なし画像特徴表現学習の動向 {Un, Self} supervised representation learning (CVPR 2…
Read more CVPR 2017 速報
Read more [MIRU 2018 招待講演] Neural 3D Mesh Renderer (CVPR 2018)
Read more CVPR 2018 速報
Read more CVPR2018 現地レポート