Simultaneous object detection and ranking with weak supervision
A standard approach to learning object category detectors is to provide strong supervision in the form of a region of interest (ROI) specifying each instance of the object in the training images. In this work are goal is to learn from heterogeneous labels, in which some images are only weakly superv...
Main Authors: | Blaschko, MB, Vedaldi, A, Zisserman, A |
---|---|
Formato: | Conference item |
Idioma: | English |
Publicado: |
Curran Associates
2011
|
Títulos similares
-
Weakly supervised deep detection networks
por: Vedaldi, A, et al.
Publicado: (2016) -
Taxonomic multi-class prediction and person layout using efficient structured ranking
por: Mittal, A, et al.
Publicado: (2012) -
Learning equivariant structured output SVM regressors
por: Vedaldi, A, et al.
Publicado: (2012) -
Dissimilarity coefficient based weakly supervised object detection
por: Arun, A, et al.
Publicado: (2020) -
Efficient Weakly-Supervised Object Detection With Pseudo Annotations
por: Qingsheng Yuan, et al.
Publicado: (2021-01-01)