diff options
author | Vasil Zlatanov <v@skozl.com> | 2019-03-22 17:43:54 +0000 |
---|---|---|
committer | Vasil Zlatanov <v@skozl.com> | 2019-03-22 17:43:54 +0000 |
commit | 5245b5ec835175d390b78f5b201e7ca5fdaaab9b (patch) | |
tree | a6cbe85e05a1f10dc56e431382e05e54e1fc4dcf /report/template.latex | |
parent | f38dcc474ce7b97f37b5a226ad66043199402b0f (diff) | |
download | e3-deep-5245b5ec835175d390b78f5b201e7ca5fdaaab9b.tar.gz e3-deep-5245b5ec835175d390b78f5b201e7ca5fdaaab9b.tar.bz2 e3-deep-5245b5ec835175d390b78f5b201e7ca5fdaaab9b.zip |
Pre final
Diffstat (limited to 'report/template.latex')
-rw-r--r-- | report/template.latex | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/report/template.latex b/report/template.latex index da5bdd2..232f8b3 100644 --- a/report/template.latex +++ b/report/template.latex @@ -47,7 +47,7 @@ %%%%%%%%% ABSTRACT \begin{abstract} - Abstract - ... + Abstract - In this paper we investigate triplet loss based methods for verification, matching and retrieval of the HPatches dataset. We explore a system of two models, one for denoising of the patches and one for generation of descriptors. We are able to show that a model trained with online hard patch mining, while more difficult, is able to achieve improved performance over a classical Siamese triplet network. \end{abstract} \providecommand{\tightlist}{% |