We present a descriptor, called fully convolutional self-similarity (FCSS), for dense semantic correspondence. Unlike traditional dense correspondence approaches for estimating depth or optical flow, semantic correspondence estimation poses additional challenges due to intra-class appearance and shape variations among different instances within the same object or scene category. To robustly match points across semantically similar images, we formulate FCSS using local self-similarity (LSS), which is inherently insensitive to intra-class appearance variations. LSS is incorporated through a proposed convolutional self-similarity (CSS) layer, where the sampling patterns and the self-similarity measure are jointly learned in an end-to-end and multi-scale manner. Furthermore, to address shape variations among different object instances, we propose a convolutional affine transformer (CAT) layer that estimates explicit affine transformation fields at each pixel to transform the sampling patterns and corresponding receptive fields. As training data for semantic correspondence is rather limited, we propose to leverage object candidate priors provided in most existing datasets and also correspondence consistency between object pairs to enable weakly-supervised learning. Experiments demonstrate that FCSS significantly outperforms conventional handcrafted descriptors and CNN-based descriptors on various benchmarks.
|Number of pages||15|
|Journal||IEEE Transactions on Pattern Analysis and Machine Intelligence|
|State||Published - 1 Mar 2019|
Bibliographical noteFunding Information:
This research was supported by Next-Generation Information Computing Development Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT (NRF-2017M3C4A7069370). The work of B. Ham was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. 2017R1C1B2005584).
© 1979-2012 IEEE.
- Dense semantic correspondence
- convolutional neural networks
- weakly-supervised learning