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...
Glavni autori: | Blaschko, MB, Vedaldi, A, Zisserman, A |
---|---|
Format: | Conference item |
Jezik: | English |
Izdano: |
Curran Associates
2011
|
Slični predmeti
-
Weakly supervised deep detection networks
od: Vedaldi, A, i dr.
Izdano: (2016) -
Taxonomic multi-class prediction and person layout using efficient structured ranking
od: Mittal, A, i dr.
Izdano: (2012) -
Learning equivariant structured output SVM regressors
od: Vedaldi, A, i dr.
Izdano: (2012) -
Dissimilarity coefficient based weakly supervised object detection
od: Arun, A, i dr.
Izdano: (2020) -
Efficient Weakly-Supervised Object Detection With Pseudo Annotations
od: Qingsheng Yuan, i dr.
Izdano: (2021-01-01)