Abstract

Deep Neural Networks (DNNs) have recently shown outstanding performance on image classification tasks [14]. In this paper we go one step further and address the problem of object detection using DNNs, that is not only classifying but also precisely localizing objects of various classes. We present a simple and yet pow-erful formulation of object detection as a regression problem to object bounding box masks. We define a multi-scale inference procedure which is able to pro-duce high-resolution object detections at a low cost by a few network applications. State-of-the-art performance of the approach is shown on Pascal VOC. 1

Keywords

Pascal (unit)Computer scienceObject detectionArtificial intelligenceInferenceMinimum bounding boxBounding overwatchDeep neural networksArtificial neural networkObject (grammar)Pattern recognition (psychology)Cognitive neuroscience of visual object recognitionDeep learningMachine learningComputer visionImage (mathematics)

Affiliated Institutions

Related Publications

Publication Info

Year
2013
Type
article
Volume
26
Pages
2553-2561
Citations
1200
Access
Closed

External Links

Citation Metrics

1200
OpenAlex

Cite This

Christian Szegedy, Alexander Toshev, Dumitru Erhan (2013). Deep Neural Networks for Object Detection. , 26 , 2553-2561.