A Tree-Based Context Model for Object Recognition

By Myung Jin Choi, Antonio Torralba, Alan S. Willsky. 2012

164 citations recorded by the source corpus.

There has been a growing interest in exploiting contextual information in addition to local features to detect and localize multiple object categories in an image. A context model can rule out some unlikely combinations or locations of objects and guide detectors to produce a semantically coherent interpretation of a scene. However, the performance benefit of context models has been limited because most of the previous methods were tested on data sets with only a few object categories, in which most images contain one or two object categories. In this paper, we introduce a new data set with images that contain many instances of different object categories, and propose an efficient model that captures the contextual information among more than a hundred object categories using a tree structure. Our model incorporates global image features, dependencies between object categories, and outputs of local detectors into one probabilistic framework. We demonstrate that our context model improves object recognition performance and provides a coherent interpretation of a scene, which enables a reliable image querying system by multiple object categories. In addition, our model can be applied to scene understanding tasks that local detectors alone cannot solve, such as detecting objects out of context or querying for the most typical and the least typical scenes in a data set.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

Discovering objects and their relations from entangled scene representations (2017, methodology): “…and Zhao & Zhu (2011) modelled relations among image features using stochastic grammars, Felzenszwalb et al. (2008) modelled relations among object parts using the “deformable parts” model, and Choi et al. (2012) modelled relations among objects in scenes using tree structured context models.”
Context models and out-of-context objects (2012, background): “Keywords:”
DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding (2016, background): “The role of context has been studied extensively in computer vision [27, 41, 5, 4, 3, 7, 18, 37, 33, 35, 34, 19, 12, 9, 43, 1, 39, 24, 10, 42, 20, 21].”
Humans, but Not Deep Neural Networks, Often Miss Giant Targets in Scenes. (2017, background): “Indeed, some studies have shown how incorporating information about likely target size can potentially reduce false positives for machine object detectors [53].”
Contextualizing Object Detection and Classification (2015, background): “23 which is slightly better than the result of [9].”
Relation-Aware Graph Attention Network for Visual Question Answering (2019, methodology): “Early work [10, 14, 7, 37] presented methods to re-score the detected objects by considering object relations (e.”
Incorporating Scene Context and Object Layout into Appearance Modeling (2014, methodology): “For improving object detection, [1] proposes an extension of non-maximum suppression that uses contextual information in the form of a single cooccurrences relation tree.”