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...
主要な著者: | Blaschko, MB, Vedaldi, A, Zisserman, A |
---|---|
フォーマット: | Conference item |
言語: | English |
出版事項: |
Curran Associates
2011
|
類似資料
-
Weakly supervised deep detection networks
著者:: Vedaldi, A, 等
出版事項: (2016) -
Taxonomic multi-class prediction and person layout using efficient structured ranking
著者:: Mittal, A, 等
出版事項: (2012) -
Learning equivariant structured output SVM regressors
著者:: Vedaldi, A, 等
出版事項: (2012) -
Dissimilarity coefficient based weakly supervised object detection
著者:: Arun, A, 等
出版事項: (2020) -
Efficient Weakly-Supervised Object Detection With Pseudo Annotations
著者:: Qingsheng Yuan, 等
出版事項: (2021-01-01)