End-to-end weakly-supervised semantic alignment

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F18%3A00329434" target="_blank" >RIV/68407700:21730/18:00329434 - isvavai.cz</a>

Result on the web

<a href="https://ieeexplore.ieee.org/document/8578821" target="_blank" >https://ieeexplore.ieee.org/document/8578821</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR.2018.00723" target="_blank" >10.1109/CVPR.2018.00723</a>

Result language

angličtina

Original language name

End-to-end weakly-supervised semantic alignment

Original language description

We tackle the task of semantic alignment where the goal is to compute dense semantic correspondence aligning two images depicting objects of the same category. This is a challenging task due to large intra-class variation, changes in viewpoint and background clutter. We present the following three principal contributions. First, we develop a convolutional neural network architecture for semantic alignment that is trainable in an end-to-end manner from weak image-level supervision in the form of matching image pairs. The outcome is that parameters are learnt from rich appearance variation present in different but semantically related images without the need for tedious manual annotation of correspondences at training time. Second, the main component of this architecture is a differentiable soft inlier scoring module, inspired by the RANSAC inlier scoring procedure, that computes the quality of the alignment based on only geometrically consistent correspondences thereby reducing the effect of background clutter. Third, we demonstrate that the proposed approach achieves state-of-the-art performance on multiple standard benchmarks for semantic alignment.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/EF15_003%2F0000468" target="_blank" >EF15_003/0000468: Intelligent Machine Perception</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2018

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

CVPR 2018: Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition

ISBN

978-1-5386-6420-9

ISSN

1063-6919

e-ISSN

2575-7075

Number of pages

9

Pages from-to

6917-6925

Publisher name

IEEE

Place of publication

Piscataway, NJ

Event location

Salt Lake City

Event date

Jun 19, 2018

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000457843607008