Active boundary annotation using random MAP perturbations
We address the problem of efficiently annotating labels of objects when they are structured. Often the distribution over labels can be described using a joint potential function over the labels for which sampling is provably hard but efficient maximum a-posteriori (MAP) solvers exist. In this settin...
Үндсэн зохиолчид: | Maji, Subhransu, Hazan, Tamir, Jaakkola, Tommi S |
---|---|
Бусад зохиолчид: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
Формат: | Өгүүллэг |
Хэл сонгох: | en_US |
Хэвлэсэн: |
PLMR
2018
|
Онлайн хандалт: | http://hdl.handle.net/1721.1/115314 https://orcid.org/0000-0002-2199-0379 |
Ижил төстэй зүйлс
-
On sampling from the Gibbs distribution with random maximum a-posteriori perturbations
-н: Hazan, Tamir, зэрэг
Хэвлэсэн: (2015) -
High Dimensional Inference with Random Maximum A-Posteriori Perturbations
-н: Maji, Subhransu, зэрэг
Хэвлэсэн: (2021) -
Learning efficient random maximum a-posteriori predictors with non-decomposable loss functions
-н: Hazan, Tamir, зэрэг
Хэвлэсэн: (2015) -
On the Partition Function and Random Maximum A-Posteriori Perturbations
-н: Hazan, Tamir, зэрэг
Хэвлэсэн: (2021) -
On the Partition Function and Random Maximum A-Posteriori Perturbations
-н: Hazan, Tamir, зэрэг
Хэвлэсэн: (2021)