# Robust Pedestrian Detection via Constructing Versatile Pedestrian Knowledge Bank

arXiv: https://arxiv.org/abs/2404.19299 · HTML: https://mlsanity.com/paper/2404.19299/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 40 references that are in the map.
- First posted on arXiv 30 Apr 2024.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [CrowdHuman: A Benchmark for Detecting Human in a Crowd](https://mlsanity.com/paper/1805.00123/) (2018)
- [CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation](https://mlsanity.com/paper/2110.02624/) (2021)
- [CityPersons: A Diverse Dataset for Pedestrian Detection](https://mlsanity.com/paper/1702.05693/) (2017)
- [Adaptive NMS: Refining Pedestrian Detection in a Crowd](https://mlsanity.com/paper/1904.03629/) (2019)
- [UniHCP: A Unified Model for Human-Centric Perceptions](https://mlsanity.com/paper/2303.02936/) (2023)
- [VT-CLIP: Enhancing Vision-Language Models with Visual-guided Texts](https://mlsanity.com/paper/2112.02399/) (2021)
- [NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing](https://mlsanity.com/paper/2003.12729/) (2020)
- [Progressive End-to-End Object Detection in Crowded Scenes](https://mlsanity.com/paper/2203.07669/) (2022)
- [On Guiding Visual Attention with Language Specification](https://mlsanity.com/paper/2202.08926/) (2022)
- [Restoring Negative Information in Few-Shot Object Detection](https://mlsanity.com/paper/2010.11714/) (2020)
- [Attribute-aware Pedestrian Detection in a Crowd](https://mlsanity.com/paper/1910.09188/) (2019)
- [Domain Aligned CLIP for Few-shot Classification](https://mlsanity.com/paper/2311.09191/) (2023)
- [IterDet: Iterative Scheme for Object Detection in Crowded Environments](https://mlsanity.com/paper/2005.05708/) (2020)
- [WIDER Face and Pedestrian Challenge 2018: Methods and Results](https://mlsanity.com/paper/1902.06854/) (2019)
- [Variational Pedestrian Detection](https://mlsanity.com/paper/2104.12389/) (2021)
- [Center and Scale Prediction: Anchor-free Approach for Pedestrian and Face Detection](https://mlsanity.com/paper/1904.02948/) (2019)
- [InDiReCT: Language-Guided Zero-Shot Deep Metric Learning for Images](https://mlsanity.com/paper/2211.12760/) (2022)

## Built on by (most cited first, 3 of 3)

- [Phantom of Latent for Large Language and Vision Models](https://mlsanity.com/paper/2409.14713/) (2024)
- [TroL: Traversal of Layers for Large Language and Vision Models](https://mlsanity.com/paper/2406.12246/) (2024)
- [Revisiting Misalignment in Multispectral Pedestrian Detection: A Language-Driven Approach for Cross-modal Alignment Fusion](https://mlsanity.com/paper/2411.17995/) (2024)

## Abstract (arXiv)

Pedestrian detection is a crucial field of computer vision research which can be adopted in various real-world applications (e.g., self-driving systems). However, despite noticeable evolution of pedestrian detection, pedestrian representations learned within a detection framework are usually limited to particular scene data in which they were trained. Therefore, in this paper, we propose a novel approach to construct versatile pedestrian knowledge bank containing representative pedestrian knowledge which can be applicable to various detection frameworks and adopted in diverse scenes. We extract generalized pedestrian knowledge from a large-scale pretrained model, and we curate them by quantizing most representative features and guiding them to be distinguishable from background scenes. Finally, we construct versatile pedestrian knowledge bank which is composed of such representations, and then we leverage it to complement and enhance pedestrian features within a pedestrian detection framework. Through comprehensive experiments, we validate the effectiveness of our method, demonstrating its versatility and outperforming state-of-the-art detection performances.