# CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection

arXiv: https://arxiv.org/abs/2212.05691 · HTML: https://mlsanity.com/paper/2212.05691/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 65 references that are in the map.
- First posted on arXiv 12 Dec 2022.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [CityPersons: A Diverse Dataset for Pedestrian Detection](https://mlsanity.com/paper/1702.05693/) (2017)
- [A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection](https://mlsanity.com/paper/1607.07155/) (2016)
- [Repulsion Loss: Detecting Pedestrians in a Crowd](https://mlsanity.com/paper/1711.07752/) (2017)
- [Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd](https://mlsanity.com/paper/1807.08407/) (2018)
- [Object detection via a multi-region & semantic segmentation-aware CNN model](https://mlsanity.com/paper/1505.01749/) (2015)
- [Person Search via A Mask-Guided Two-Stream CNN Model](https://mlsanity.com/paper/1807.08107/) (2018)
- [Is Faster R-CNN Doing Well for Pedestrian Detection?](https://mlsanity.com/paper/1607.07032/) (2016)
- [Towards Accurate One-Stage Object Detection with AP-Loss](https://mlsanity.com/paper/1904.06373/) (2019)
- [Scale-aware Fast R-CNN for Pedestrian Detection](https://mlsanity.com/paper/1510.08160/) (2015)
- [How Far are We from Solving Pedestrian Detection?](https://mlsanity.com/paper/1602.01237/) (2016)
- [What Can Help Pedestrian Detection?](https://mlsanity.com/paper/1705.02757/) (2017)
- [Illuminating Pedestrians via Simultaneous Detection & Segmentation](https://mlsanity.com/paper/1706.08564/) (2017)
- [Taking a Deeper Look at Pedestrians](https://mlsanity.com/paper/1501.05790/) (2015)
- [Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages](https://mlsanity.com/paper/1807.11013/) (2018)
- [A MultiPath Network for Object Detection](https://mlsanity.com/paper/1604.02135/) (2016)
- [Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection](https://mlsanity.com/paper/1610.03466/) (2016)
- [PCN: Part and Context Information for Pedestrian Detection with CNNs](https://mlsanity.com/paper/1804.04483/) (2018)
- [Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model](https://mlsanity.com/paper/1611.07544/) (2016)

## Abstract (arXiv)

Pedestrian detection in the wild remains a challenging problem especially when the scene contains significant occlusion and/or low resolution of the pedestrians to be detected. Existing methods are unable to adapt to these difficult cases while maintaining acceptable performance. In this paper we propose a novel feature learning model, referred to as CircleNet, to achieve feature adaptation by mimicking the process humans looking at low resolution and occluded objects: focusing on it again, at a finer scale, if the object can not be identified clearly for the first time. CircleNet is implemented as a set of feature pyramids and uses weight sharing path augmentation for better feature fusion. It targets at reciprocating feature adaptation and iterative object detection using multiple top-down and bottom-up pathways. To take full advantage of the feature adaptation capability in CircleNet, we design an instance decomposition training strategy to focus on detecting pedestrian instances of various resolutions and different occlusion levels in each cycle. Specifically, CircleNet implements feature ensemble with the idea of hard negative boosting in an end-to-end manner. Experiments on two pedestrian detection datasets, Caltech and CityPersons, show that CircleNet improves the performance of occluded and low-resolution pedestrians with significant margins while maintaining good performance on normal instances.