Atrous Faster R-CNN for Small Scale Object Detection

Tongfan Guan, Hao Zhu

Abstract:

Deep Convolutional Neural Networks based object
detection has made significant progress recent years. However,
detecting small scale objects is still a challenging task. This
paper addresses the problem and proposes a unified deep
neural network building upon the prominent Faster R-CNN
framework. This paper has two main contributions. Firstly, an
Atrous Region Proposal Network (ARPN) is proposed to
explore object contexts at multiple scales by sliding a set of
atrous filters with increasing dilation rates over the last
convolutional feature map. Secondly, to enrich the
representations of small scale image regions, this paper
incorporates atrous convolution into Fast R-CNN and
proposes a Dense Fast R-CNN (DFRCN), that improves the
resolution of the ROI-pooled convolutional feature maps
without increasing the number of parameters. In combination
of the two, this paper proposes a unified network termed as
Atrous Faster R-CNN. On PASCAL object detection challenge
dataset, our method achieves superior performance to the
state of the arts, especially for small scale objects.