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...
Main Authors: | Novotny, D, Larlus, D, Vedaldi, A |
---|---|
格式: | Conference item |
出版: |
Institute of Electrical and Electronics Engineers
2017
|
相似書籍
-
Capturing the geometry of object categories from video supervision
由: Novotny, D, et al.
出版: (2018) -
Learning the semantic structure of objects from Web supervision
由: Novotny, D, et al.
出版: (2016) -
Self-supervised learning of geometrically stable features through probabilistic introspection
由: Novotny, D, et al.
出版: (2018) -
RSS-Net: weakly-supervised multi-class semantic segmentation with FMCW radar
由: Kaul, P, et al.
出版: (2021) -
Neural feature fusion fields: 3D distillation of self-supervised 2D image representations
由: Tschernezki, V, et al.
出版: (2023)