# Non-Hierarchical Transformers for Pedestrian Segmentation

arXiv: https://arxiv.org/abs/2311.02506 · HTML: https://mlsanity.com/paper/2311.02506/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 5 references that are in the map.
- First posted on arXiv 11 Jul 2023.

## Builds on (most cited first, 4 of 4)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (2019)
- [EVA-02: A Visual Representation for Neon Genesis](https://mlsanity.com/paper/2303.11331/) (2023)

## Abstract (arXiv)

We propose a methodology to address the challenge of instance segmentation in autonomous systems, specifically targeting accessibility and inclusivity. Our approach utilizes a non-hierarchical Vision Transformer variant, EVA-02, combined with a Cascade Mask R-CNN mask head. Through fine-tuning on the AVA instance segmentation challenge dataset, we achieved a promising mean Average Precision (mAP) of 52.68% on the test set. Our results demonstrate the efficacy of ViT-based architectures in enhancing vision capabilities and accommodating the unique needs of individuals with disabilities.