Contextual models for object detection using boosted random fields
Antonio B. Torralba, Kevin P. Murphy, William T. Freeman · DSpace@MIT (Massachusetts Institute of Technology) · 2004
We seek to both detect and segment objects in images. To exploit both lo-cal image data as well as contextual information, we introduce Boosted Random Fields (BRFs), which uses Boosting to learn the graph struc-ture and local evidence of a conditional random field (CRF). The graph structure is learned by assembling graph fragments in an additive model. The connections between individual pixels are not very informative, but by using dense graphs, we can pool information from large regions of the image; dense models also support efficient inference. We show how contextual information from other objects can improve detection perfor-mance, both in terms of accuracy and speed, by using a computational cascade. We apply our system to detect stuff and things in office and street scenes. 1
Cited by 300 works. Open-access PDF
Authors
References
- Robust Real-Time Face Detection
- Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
- Additive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors)
- Multiscale conditional random fields for image labeling
- Class-Specific, Top-Down Segmentation
- Max-Margin Markov Networks
- The Boosting Approach to Machine Learning: An Overview
- Discriminative random fields: a discriminative framework for contextual interaction in classification
- Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes
- On seeing stuff: the perception of materials by humans and machines