Context models and out-of-context objects

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

142 citations recorded by the source corpus.

Highlights? Review of different sources of contextual information for object detection. ? New context model based on capturing support relationships and co-occurrences among objects. ? Evaluation of several context models on the SUN database. ? Introduction of a benchmark for detecting out-of-context objects. The context of an image encapsulates rich information about how natural scenes and objects are related to each other. Such contextual information has the potential to enable a coherent understanding of natural scenes and images. However, context models have been evaluated mostly based on the improvement of object recognition performance even though it is only one of many ways to exploit contextual information. In this paper, we present a new scene understanding problem for evaluating and applying context models. We are interested in finding scenes and objects that are "out-of-context". Detecting "out-of-context" objects and scenes is challenging because context violations can be detected only if the relationships between objects are carefully and precisely modeled. To address this problem, we evaluate different sources of context information, and present a graphical model that combines these sources. We show that physical support relationships between objects can provide useful contextual information for both object recognition and out-of-context detection.

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

Weakly-Supervised Learning of Visual Relations (2017, methodology): “Our dataset is related to the “Out of context” dataset of [7] which also presents objects in unusual conﬁgurations.”
REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets (2020, background): “…(Buda et al., 2017; Liu et al., 2009; Oksuz et al., 2019; Ouyang et al., 2016; Salakhutdinov et al., 2011; J. Yang et al., 2014), object contexts (Choi et al., 2012; Rosenfeld et al., 2018), object sub-categories (Zhu et al., 2014), scenes (Zhou et al., 2017), gender (Kay et al., 2015), gender…”
Teaching Compositionality to CNNs (2017, background): “Our environment tends to be highly regular, and making use of regularities in the occurrence of different object and scene classes has been shown to be beneficial for recognizing familiar objects [25, 4], objects in unusual circumstances [3], and recurring spatial configurations [7, 30, 11, 46].”
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].”