A multi-plane block-coordinate frank-wolfe algorithm for training structural SVMs with a costly max-oracle
By Neel Shah, Vladimir Kolmogorov, Christoph H. Lampert. 2014
23 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Optimization & Training
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Simon Lacoste-Julien
- Jean-Baptiste Alayrac
- Cordelia Schmid
- Ivan Laptev
- Luc Van Gool
- Puneet Kumar Dokania
- Andrew Zisserman
- Anton Osokin
In Optimization & Training
- Jean-Baptiste Alayrac
- Simon Lacoste-Julien
- Anton Osokin
- Puneet Kumar Dokania
- Isabella Lukasewitz
- Peter Richtárik
- Martin Jaggi
- Ivan Laptev
Citations in the corpus
- Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs (2016, methodology): “In contrast to Shah et al. (2015), our method chooses whether to call the oracle or to use the cache in an adaptive way by looking at the gap estimates of the current blocks.”