|
ИСТИНА |
Войти в систему Регистрация |
ИСТИНА ИНХС РАН |
||
Deep Part-Based Generative Shape Model with Latent Variablesстатья
- Авторы: Alexander Kirillov, Mikhail Gavrikov, Ekaterina Lobacheva, Anton Osokin, Dmitry Vetrov
- Сборник: British Machine Vision Conference (BMVC 2016)
- Год издания: 2016
- Место издания: York, United Kingdom
- Первая страница: 1
- Последняя страница: 11
- Аннотация: The Shape Boltzmann Machine (SBM)[6] and its multilabel version MSBM [5] have been recently introduced as deep generative models that capture the variations of an object shape. While being more flexible MSBM requires datasets with labeled parts of the objects for training. In the paper we present an algorithm for training MSBM using binary masks of objects and the seeds which approximately correspond to the locations of objects parts. The latter can be obtained from part-based detectors in an unsupervised manner.
- Добавил в систему: Журавлев Юрий Иванович