# What Can Help Pedestrian Detection?

arXiv: https://arxiv.org/abs/1705.02757 · HTML: https://mlsanity.com/paper/1705.02757/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2017.

## Built on by (most cited first, 26 of 26)

- [Weakly Aligned Feature Fusion for Multimodal Object Detection](https://mlsanity.com/paper/2204.09848/) (2022)
- [Multi-Source Domain Adaptation for Object Detection](https://mlsanity.com/paper/2106.15793/) (2021)
- [LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration](https://mlsanity.com/paper/2410.15385/) (2024)
- [MS-DETR: Multispectral Pedestrian Detection Transformer with Loosely Coupled Fusion and Modality-Balanced Optimization](https://mlsanity.com/paper/2302.00290/) (2023)
- [Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes](https://mlsanity.com/paper/2407.11464/) (2024)
- [Cross-Modality Proposal-guided Feature Mining for Unregistered RGB-Thermal Pedestrian Detection](https://mlsanity.com/paper/2308.12111/) (2023)
- [Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond](https://mlsanity.com/paper/2201.03176/) (2022)
- [GeNIe: Generative Hard Negative Images Through Diffusion](https://mlsanity.com/paper/2312.02548/) (2023)
- [NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection](https://mlsanity.com/paper/2106.02426/) (2021)
- [Multi-Modal Pedestrian Detection with Large Misalignment Based on Modal-Wise Regression and Multi-Modal IoU](https://mlsanity.com/paper/2107.11196/) (2021)
- [Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation](https://mlsanity.com/paper/2212.06242/) (2022)
- [Feature Calibration Network for Occluded Pedestrian Detection](https://mlsanity.com/paper/2212.05717/) (2022)
- [HoughLaneNet: Lane Detection with Deep Hough Transform and Dynamic Convolution](https://mlsanity.com/paper/2307.03494/) (2023)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [End-to-end Rain Streak Removal with RAW Images](https://mlsanity.com/paper/2312.13304/) (2023)
- [Fast and Accurate Image Restoration and Generation with Rank Enhanced Linear Attention](https://mlsanity.com/paper/2505.16157/) (2025)
- [Beyond Classification: Knowledge Distillation using Multi-Object Impressions](https://mlsanity.com/paper/2110.14215/) (2021)
- [Pedestrian Detection by Exemplar-Guided Contrastive Learning](https://mlsanity.com/paper/2111.08974/) (2021)
- [The Impact of Partial Occlusion on Pedestrian Detectability](https://mlsanity.com/paper/2205.04812/) (2022)
- [Data Augmentation in Human-Centric Vision](https://mlsanity.com/paper/2403.08650/) (2024)
- [Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection](https://mlsanity.com/paper/2511.10308/) (2025)
- [Finding a Needle in a Haystack: Tiny Flying Object Detection in 4K Videos using a Joint Detection-and-Tracking Approach](https://mlsanity.com/paper/2105.08253/) (2021)
- [P2P-Loc: Point to Point Tiny Person Localization](https://mlsanity.com/paper/2112.15344/) (2021)
- [CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection](https://mlsanity.com/paper/2212.05691/) (2022)
- [t-RAIN: Robust generalization under weather-aliasing label shift attacks](https://mlsanity.com/paper/2305.08302/) (2023)
- [Learning 3D Texture-Aware Representations for Parsing Diverse Human Clothing and Body Parts](https://mlsanity.com/paper/2508.06032/) (2025)

## Abstract (arXiv)

Aggregating extra features has been considered as an effective approach to boost traditional pedestrian detection methods. However, there is still a lack of studies on whether and how CNN-based pedestrian detectors can benefit from these extra features. The first contribution of this paper is exploring this issue by aggregating extra features into CNN-based pedestrian detection framework. Through extensive experiments, we evaluate the effects of different kinds of extra features quantitatively. Moreover, we propose a novel network architecture, namely HyperLearner, to jointly learn pedestrian detection as well as the given extra feature. By multi-task training, HyperLearner is able to utilize the information of given features and improve detection performance without extra inputs in inference. The experimental results on multiple pedestrian benchmarks validate the effectiveness of the proposed HyperLearner.