Accurate Single Stage Detector Using Recurrent Rolling Convolution

TL;DR

This paper introduces a novel single-stage object detection network using Recurrent Rolling Convolution to enhance multi-scale features, achieving state-of-the-art results on the KITTI dataset for high IoU thresholds.

Contribution

The paper proposes Recurrent Rolling Convolution architecture for single-stage detection, significantly improving accuracy over previous methods on challenging benchmarks.

Findings

Outperformed all previous single-stage methods on KITTI dataset

Achieved first place in car and cyclist detection, second in pedestrian detection

Model based on reduced VGG-16 outperforms existing benchmarks

Abstract

Most of the recent successful methods in accurate object detection and localization used some variants of R-CNN style two stage Convolutional Neural Networks (CNN) where plausible regions were proposed in the first stage then followed by a second stage for decision refinement. Despite the simplicity of training and the efficiency in deployment, the single stage detection methods have not been as competitive when evaluated in benchmarks consider mAP for high IoU thresholds. In this paper, we proposed a novel single stage end-to-end trainable object detection network to overcome this limitation. We achieved this by introducing Recurrent Rolling Convolution (RRC) architecture over multi-scale feature maps to construct object classifiers and bounding box regressors which are "deep in context". We evaluated our method in the challenging KITTI dataset which measures methods under IoU threshold of 0.7. We showed that with RRC, a single reduced VGG-16 based model already significantly outperformed all the previously published results. At the time this paper was written our models ranked the first in KITTI car detection (the hard level), the first in cyclist detection and the second in pedestrian detection. These results were not reached by the previous single stage methods. The code is publicly available.