Learning a Layout Transfer Network for Context Aware Object Detection

Abstract

We present a context aware object detection method based on a retrieve-and-transform scene layout model. Given an input image, our approach first retrieves a coarse scene layout from a codebook of typical layout templates. In order to handle large layout variations, we use a variant of the spatial transformer network to transform and refine the retrieved layout, resulting in a set of interpretable and semantically meaningful feature maps of object locations and scales. The above steps are implemented as a Layout Transfer Network which we integrate into Faster RCNN to allow for joint reasoning of object detection and scene layout estimation. Extensive experiments on three public datasets verified that our approach provides consistent performance improvements to the state-of-the-art object detection baselines on a variety of challenging tasks in the traffic surveillance and the autonomous driving domains.

Paper accepted by the IEEE Transactions on Intelligent Transportation Systems

References in corpus (6)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• SINet: A Scale-insensitive Convolutional Neural Network for Fast Vehicle Detection
• Fast detection of multiple objects in traffic scenes with a common detection framework
• Learning from Maps: Visual Common Sense for Autonomous Driving

Cited by in corpus (2)

• Context in object detection: a systematic literature review
• Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes