AnchorNet: A weakly supervised network to learn geometry-sensitive features for semantic matching

Despite significant progress of deep learning in recent years, state-of-the-art semantic matching methods still rely on legacy features such as SIFT or HoG. We argue that the strong invariance properties that are key to the success of recent deep architectures on the classification task make them un...

Полное описание

Библиографические подробности
Главные авторы: Novotny, D, Larlus, D, Vedaldi, A
Формат: Conference item
Опубликовано: Institute of Electrical and Electronics Engineers 2017

Схожие документы