# Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection

arXiv: https://arxiv.org/abs/1610.03466 · HTML: https://mlsanity.com/paper/1610.03466/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2016.

## Built on by (most cited first, 10 of 10)

- [NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection](https://mlsanity.com/paper/2106.02426/) (2021)
- [Whole-body Detection, Recognition and Identification at Altitude and Range](https://mlsanity.com/paper/2311.05725/) (2023)
- [Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network](https://mlsanity.com/paper/2009.14563/) (2020)
- [Feature Calibration Network for Occluded Pedestrian Detection](https://mlsanity.com/paper/2212.05717/) (2022)
- [A Lightweight Measure of Classification Difficulty from Application Dataset Characteristics](https://mlsanity.com/paper/2404.05981/) (2024)
- [Pedestrian Detection by Exemplar-Guided Contrastive Learning](https://mlsanity.com/paper/2111.08974/) (2021)
- [Which to Match? Selecting Consistent GT-Proposal Assignment for Pedestrian Detection](https://mlsanity.com/paper/2103.10091/) (2021)
- [CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection](https://mlsanity.com/paper/2212.05691/) (2022)
- [Low-light Pedestrian Detection in Visible and Infrared Image Feeds: Issues and Challenges](https://mlsanity.com/paper/2311.08557/) (2023)
- [Efficient Neural Network Model Selection for Few-Class Application Datasets](https://mlsanity.com/paper/2606.19712/) (2026)

## Abstract (arXiv)

We propose a deep neural network fusion architecture for fast and robust pedestrian detection. The proposed network fusion architecture allows for parallel processing of multiple networks for speed. A single shot deep convolutional network is trained as a object detector to generate all possible pedestrian candidates of different sizes and occlusions. This network outputs a large variety of pedestrian candidates to cover the majority of ground-truth pedestrians while also introducing a large number of false positives. Next, multiple deep neural networks are used in parallel for further refinement of these pedestrian candidates. We introduce a soft-rejection based network fusion method to fuse the soft metrics from all networks together to generate the final confidence scores. Our method performs better than existing state-of-the-arts, especially when detecting small-size and occluded pedestrians. Furthermore, we propose a method for integrating pixel-wise semantic segmentation network into the network fusion architecture as a reinforcement to the pedestrian detector. The approach outperforms state-of-the-art methods on most protocols on Caltech Pedestrian dataset, with significant boosts on several protocols. It is also faster than all other methods.