# Accurate Single Stage Detector Using Recurrent Rolling Convolution

arXiv: https://arxiv.org/abs/1704.05776 · HTML: https://mlsanity.com/paper/1704.05776/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2017.

## Built on by (most cited first, 27 of 27)

- [EagerMOT: 3D Multi-Object Tracking via Sensor Fusion](https://mlsanity.com/paper/2104.14682/) (2021)
- [From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection](https://mlsanity.com/paper/2304.13455/) (2023)
- [DeepFusionMOT: A 3D Multi-Object Tracking Framework Based on Camera-LiDAR Fusion with Deep Association](https://mlsanity.com/paper/2202.12100/) (2022)
- [TrackMPNN: A Message Passing Graph Neural Architecture for Multi-Object Tracking](https://mlsanity.com/paper/2101.04206/) (2021)
- [Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.14829/) (2021)
- [Multi-Camera Multiple 3D Object Tracking on the Move for Autonomous Vehicles](https://mlsanity.com/paper/2204.09151/) (2022)
- [CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation](https://mlsanity.com/paper/2311.00987/) (2023)
- [PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search](https://mlsanity.com/paper/2403.15712/) (2024)
- [You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object Tracking](https://mlsanity.com/paper/2304.08709/) (2023)
- [NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection](https://mlsanity.com/paper/2106.02426/) (2021)
- [CFTrack: Center-based Radar and Camera Fusion for 3D Multi-Object Tracking](https://mlsanity.com/paper/2107.05150/) (2021)
- [Multi-Camera Multi-Object Tracking on the Move via Single-Stage Global Association Approach](https://mlsanity.com/paper/2211.09663/) (2022)
- [DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustment](https://mlsanity.com/paper/2209.14965/) (2022)
- [Vulnerable Road User Detection and Safety Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2405.19202/) (2024)
- [Interactive Multi-scale Fusion of 2D and 3D Features for Multi-object Tracking](https://mlsanity.com/paper/2203.16268/) (2022)
- [DFR-FastMOT: Detection Failure Resistant Tracker for Fast Multi-Object Tracking Based on Sensor Fusion](https://mlsanity.com/paper/2302.14807/) (2023)
- [Deep Event-based Object Detection in Autonomous Driving: A Survey](https://mlsanity.com/paper/2405.03995/) (2024)
- [Seg2Track-SAM2: SAM2-based Multi-object Tracking and Segmentation](https://mlsanity.com/paper/2509.11772/) (2025)
- [A Comprehensive Safety Metric to Evaluate Perception in Autonomous Systems](https://mlsanity.com/paper/2512.14367/) (2025)
- [High-temporal-resolution event-based vehicle detection and tracking](https://mlsanity.com/paper/2212.14289/) (2022)
- [Real-time Traffic Object Detection for Autonomous Driving](https://mlsanity.com/paper/2402.00128/) (2024)
- [HoughNet: Integrating near and long-range evidence for visual detection](https://mlsanity.com/paper/2104.06773/) (2021)
- [CrossTracker: Robust Multi-modal 3D Multi-Object Tracking via Cross Correction](https://mlsanity.com/paper/2411.18850/) (2024)
- [A Robust Pedestrian Detection Approach for Autonomous Vehicles](https://mlsanity.com/paper/2210.10489/) (2022)
- [3D-FFS: Faster 3D object detection with Focused Frustum Search in sensor fusion based networks](https://mlsanity.com/paper/2103.08294/) (2021)
- [Content-adaptive Representation Learning for Fast Image Super-resolution](https://mlsanity.com/paper/2105.09645/) (2021)
- [PolyTrack: Tracking with Bounding Polygons](https://mlsanity.com/paper/2111.01606/) (2021)

## Abstract (arXiv)

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.