Discriminative Maximum Margin Image Object Categorization with Exact Inference
Qinfeng Shi, Li Cheng, Luping Zhou and Dale Schuurmans
In: The 5th International Conference on Image and Graphics, 20-23 Sep, 2009, Xi'an, China.
Categorizing multiple objects in images is essentially a
structured prediction problem: the label of an object is in
general dependent on the labels of other objects in the image.
We explicitly model object dependencies in a sparse
graphical topology induced by the adjacency of objects in
the image, which benefits inference, and then use maximum
margin principle to learn the model discriminatively. Moreover,
we propose a novel exact inference method, which
is used in training to find the most violated constraint required
by cutting plane method. A slightly modified inference
method is used in testing when the target labels
are unseen. Experiment results on both synthetic and real
datasets demonstrate the improvement of the proposed approach over the state-of-the-art methods.
|EPrint Type:||Conference or Workshop Item (Oral)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Deposited By:||Qinfeng Shi|
|Deposited On:||25 February 2010|