A closer look: Small object detection in faster R-CNN

Faster R-CNN is a well-known approach for object detection which combines the generation of region proposals and their classification into a single pipeline. In this paper we apply Faster R-CNN to the task of company logo detection. Motivated by the weak performance of Faster R-CNN on small object instances, we perform a detailed examination of both the proposal and the classification stage, examining their behavior for a wide range of object sizes. Additionally, we look at the influence of feature map resolution on the performance of those stages. We introduce an improved scheme for generating anchor proposals and propose a modification to Faster R-CNN which leverages higher-resolution feature maps for small objects. We evaluate our approach on the Flicker data set improving the detection performance on small object instances.

1. Introduction

Current object detection pipelines like Fast(er) R-CNN [1] [2] are built on deep neural networks whose convolutional layers extract increasingly abstract feature representations by applying previously learned convolutions followed by a non-linear activation function to the image. During this process, the intermediate feature maps are usually downsampled multiple times using max-pooling.