# Pedestrian Detection with Autoregressive Network Phases

arXiv: https://arxiv.org/abs/1812.00440 · HTML: https://mlsanity.com/paper/1812.00440/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2018.

## Built on by (most cited first, 12 of 12)

- [PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization](https://mlsanity.com/paper/2103.10596/) (2021)
- [GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.17202/) (2021)
- [VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision](https://mlsanity.com/paper/2304.03135/) (2023)
- [Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction](https://mlsanity.com/paper/2104.00858/) (2021)
- [Unleashing the Power of Chain-of-Prediction for Monocular 3D Object Detection](https://mlsanity.com/paper/2505.04594/) (2025)
- [NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection](https://mlsanity.com/paper/2106.02426/) (2021)
- [Deep Learning based Computer Vision Methods for Complex Traffic Environments Perception: A Review](https://mlsanity.com/paper/2211.05120/) (2022)
- [PrObeD: Proactive Object Detection Wrapper](https://mlsanity.com/paper/2310.18788/) (2023)
- [Towards Intrinsic-Aware Monocular 3D Object Detection](https://mlsanity.com/paper/2603.27059/) (2026)
- [Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian Detection](https://mlsanity.com/paper/2305.10801/) (2023)
- [Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completion](https://mlsanity.com/paper/2405.01311/) (2024)
- [Which to Match? Selecting Consistent GT-Proposal Assignment for Pedestrian Detection](https://mlsanity.com/paper/2103.10091/) (2021)

## Abstract (arXiv)

We present an autoregressive pedestrian detection framework with cascaded phases designed to progressively improve precision. The proposed framework utilizes a novel lightweight stackable decoder-encoder module which uses convolutional re-sampling layers to improve features while maintaining efficient memory and runtime cost. Unlike previous cascaded detection systems, our proposed framework is designed within a region proposal network and thus retains greater context of nearby detections compared to independently processed RoI systems. We explicitly encourage increasing levels of precision by assigning strict labeling policies to each consecutive phase such that early phases develop features primarily focused on achieving high recall and later on accurate precision. In consequence, the final feature maps form more peaky radial gradients emulating from the centroids of unique pedestrians. Using our proposed autoregressive framework leads to new state-of-the-art performance on the reasonable and occlusion settings of the Caltech pedestrian dataset, and achieves competitive state-of-the-art performance on the KITTI dataset.