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...
Главные авторы: | Novotny, D, Larlus, D, Vedaldi, A |
---|---|
Формат: | Conference item |
Опубликовано: |
Institute of Electrical and Electronics Engineers
2017
|
Схожие документы
-
Learning the semantic structure of objects from Web supervision
по: Novotny, D, и др.
Опубликовано: (2016) -
Capturing the geometry of object categories from video supervision
по: Novotny, D, и др.
Опубликовано: (2018) -
Self-supervised learning of geometrically stable features through probabilistic introspection
по: Novotny, D, и др.
Опубликовано: (2018) -
RSS-Net: weakly-supervised multi-class semantic segmentation with FMCW radar
по: Kaul, P, и др.
Опубликовано: (2021) -
Weakly supervised deep detection networks
по: Vedaldi, A, и др.
Опубликовано: (2016)