Contextual Object Detection with a Few Relevant Neighbors

by   Ehud Barnea, et al.

A natural way to improve the detection of objects is to consider the contextual constraints imposed by the detection of additional objects in a given scene. In this work, we exploit the spatial relations between objects in order to improve detection capacity, as well as analyze various properties of the contextual object detection problem. To precisely calculate context-based probabilities of objects, we developed a model that examines the interactions between objects in an exact probabilistic setting, in contrast to previous methods that typically utilize approximations based on pairwise interactions. Such a scheme is facilitated by the single realistic assumption that the existence of an object in any given location is influenced by only few informative locations in space. Based on this assumption, we suggest a method for identifying these relevant locations and integrating them into an exact calculation of probability based on their raw detector responses. This scheme is shown to improve detection results and provides unique insights about the process of contextual inference for object detection. We show that it is generally difficult to learn that a particular object reduces the probability of another, and that in cases when the context and detector strongly disagree this learning becomes virtually impossible for the purposes of improving the results of an object detector. Finally, we demonstrate improved detection results through use of our approach as applied to the PASCAL VOC dataset.


page 2

page 5

page 7

page 8


Contextual Relabelling of Detected Objects

Contextual information, such as the co-occurrence of objects and the spa...

On the Utility of Context (or the Lack Thereof) for Object Detection

The recurring context in which objects appear holds valuable information...

Object detection can be improved using human-derived contextual expectations

Each object in the world occurs in a specific context: cars are seen on ...

Inner-Scene Similarities as a Contextual Cue for Object Detection

Using image context is an effective approach for improving object detect...

Boosting in Location Space

The goal of object detection is to find objects in an image. An object d...

Adversarial Patches Exploiting Contextual Reasoning in Object Detection

The usefulness of spatial context in most fast object detection algorith...

Obj-GloVe: Scene-Based Contextual Object Embedding

Recently, with the prevalence of large-scale image dataset, the co-occur...

Please sign up or login with your details

Forgot password? Click here to reset