Timezone: »
Compositional models provide an elegant formalism for representing the visual appearance of highly variable objects. While such models are appealing from a theoretical point of view, it has been difficult to demonstrate that they lead to performance advantages on challenging datasets. Here we develop a grammar model for person detection and show that it outperforms previous high-performance systems on the PASCAL benchmark. Our model represents people using a hierarchy of deformable parts, variable structure and an explicit model of occlusion for partially visible objects. To train the model, we introduce a new discriminative framework for learning structured prediction models from weakly-labeled data.
Author Information
Ross B Girshick (UC Berkeley)
Pedro Felzenszwalb (Brown University)
David Mcallester (Toyota Tech Institute Chicago)
Related Events (a corresponding poster, oral, or spotlight)
-
2011 Poster: Object Detection with Grammar Models »
Wed. Dec 14th 04:45 -- 10:59 PM Room
More from the Same Authors
-
2017 Poster: Exploring Generalization in Deep Learning »
Behnam Neyshabur · Srinadh Bhojanapalli · David Mcallester · Nati Srebro -
2014 Poster: Discriminative Metric Learning by Neighborhood Gerrymandering »
Shubhendu Trivedi · David Mcallester · Greg Shakhnarovich -
2014 Poster: Multiscale Fields of Patterns »
Pedro Felzenszwalb · John G Oberlin -
2013 Workshop: Deep Learning »
Yoshua Bengio · Hugo Larochelle · Russ Salakhutdinov · Tomas Mikolov · Matthew D Zeiler · David Mcallester · Nando de Freitas · Josh Tenenbaum · Jian Zhou · Volodymyr Mnih -
2011 Poster: Generalization Bounds and Consistency for Latent Structural Probit and Ramp Loss »
David Mcallester · Joseph Keshet -
2011 Oral: Generalization Bounds and Consistency for Latent Structural Probit and Ramp Loss »
David Mcallester · Joseph Keshet