# F2DNet: Fast Focal Detection Network for Pedestrian Detection

arXiv: https://arxiv.org/abs/2203.02331 · HTML: https://mlsanity.com/paper/2203.02331/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 4 Mar 2022.

## Builds on (most cited first, 24 of 24)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [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)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [Repulsion Loss: Detecting Pedestrians in a Crowd](https://mlsanity.com/paper/1711.07752/) (2017)
- [The EuroCity Persons Dataset: A Novel Benchmark for Object Detection](https://mlsanity.com/paper/1805.07193/) (2018)
- [Mask-Guided Attention Network for Occluded Pedestrian Detection](https://mlsanity.com/paper/1910.06160/) (2019)
- [How Far are We from Solving Pedestrian Detection?](https://mlsanity.com/paper/1602.01237/) (2016)
- [Attribute-aware Pedestrian Detection in a Crowd](https://mlsanity.com/paper/1910.09188/) (2019)
- [Generalizable Pedestrian Detection: The Elephant In The Room](https://mlsanity.com/paper/2003.08799/) (2020)
- [Adapted Center and Scale Prediction: More Stable and More Accurate](https://mlsanity.com/paper/2002.09053/) (2020)
- [DETR for Crowd Pedestrian Detection](https://mlsanity.com/paper/2012.06785/) (2020)

## Built on by (most cited first, 6 of 6)

- [Real-time Traffic Object Detection for Autonomous Driving](https://mlsanity.com/paper/2402.00128/) (2024)
- [Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completion](https://mlsanity.com/paper/2405.01311/) (2024)
- [MSMVD: Exploiting Multi-scale Image Features via Multi-scale BEV Features for Multi-view Pedestrian Detection](https://mlsanity.com/paper/2508.20447/) (2025)
- [Beyond Overall Accuracy: Pose- and Occlusion-driven Fairness Analysis in Pedestrian Detection for Autonomous Driving](https://mlsanity.com/paper/2509.26166/) (2025)
- [Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection](https://mlsanity.com/paper/2511.10308/) (2025)
- [oTTC: Object Time-to-Contact for Motion Estimation in Autonomous Driving](https://mlsanity.com/paper/2405.07698/) (2024)

## Abstract (arXiv)

Two-stage detectors are state-of-the-art in object detection as well as pedestrian detection. However, the current two-stage detectors are inefficient as they do bounding box regression in multiple steps i.e. in region proposal networks and bounding box heads. Also, the anchor-based region proposal networks are computationally expensive to train. We propose F2DNet, a novel two-stage detection architecture which eliminates redundancy of current two-stage detectors by replacing the region proposal network with our focal detection network and bounding box head with our fast suppression head. We benchmark F2DNet on top pedestrian detection datasets, thoroughly compare it against the existing state-of-the-art detectors and conduct cross dataset evaluation to test the generalizability of our model to unseen data. Our F2DNet achieves 8.7%, 2.2%, and 6.1% MR-2 on City Persons, Caltech Pedestrian, and Euro City Person datasets respectively when trained on a single dataset and reaches 20.4% and 26.2% MR-2 in heavy occlusion setting of Caltech Pedestrian and City Persons datasets when using progressive fine-tunning. Furthermore, F2DNet have significantly lesser inference time compared to the current state-of-the-art. Code and trained models will be available at https://github.com/AbdulHannanKhan/F2DNet.