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...
Autori principali: | Blaschko, MB, Vedaldi, A, Zisserman, A |
---|---|
Natura: | Conference item |
Lingua: | English |
Pubblicazione: |
Curran Associates
2011
|
Documenti analoghi
Documenti analoghi
-
Weakly supervised deep detection networks
di: Vedaldi, A, et al.
Pubblicazione: (2016) -
Taxonomic multi-class prediction and person layout using efficient structured ranking
di: Mittal, A, et al.
Pubblicazione: (2012) -
Learning equivariant structured output SVM regressors
di: Vedaldi, A, et al.
Pubblicazione: (2012) -
Dissimilarity coefficient based weakly supervised object detection
di: Arun, A, et al.
Pubblicazione: (2020) -
Efficient Weakly-Supervised Object Detection With Pseudo Annotations
di: Qingsheng Yuan, et al.
Pubblicazione: (2021-01-01)