Object Detectors Emerge in Deep Scene CNNs

TL;DR

This paper demonstrates that CNNs trained for scene classification naturally develop object detectors, enabling simultaneous scene recognition and object localization without explicit object training.

Contribution

It reveals that object detectors emerge in CNNs trained for scene classification, showing a shared representation for scene and object recognition.

Findings

Object detectors emerge in CNNs trained for scene classification

CNNs can perform object localization without explicit object training

Single forward-pass enables both scene recognition and object detection

Abstract

With the success of new computational architectures for visual processing, such as convolutional neural networks (CNN) and access to image databases with millions of labeled examples (e.g., ImageNet, Places), the state of the art in computer vision is advancing rapidly. One important factor for continued progress is to understand the representations that are learned by the inner layers of these deep architectures. Here we show that object detectors emerge from training CNNs to perform scene classification. As scenes are composed of objects, the CNN for scene classification automatically discovers meaningful objects detectors, representative of the learned scene categories. With object detectors emerging as a result of learning to recognize scenes, our work demonstrates that the same network can perform both scene recognition and object localization in a single forward-pass, without ever having been explicitly taught the notion of objects.