# A Cross-Scale Hierarchical Transformer with Correspondence-Augmented Attention for inferring Bird's-Eye-View Semantic Segmentation

arXiv: https://arxiv.org/abs/2304.03650 · HTML: https://mlsanity.com/paper/2304.03650/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 58 references that are in the map.
- First posted on arXiv 7 Apr 2023.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [Argoverse: 3D Tracking and Forecasting with Rich Maps](https://mlsanity.com/paper/1911.02620/) (2019)
- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [NICE-SLAM: Neural Implicit Scalable Encoding for SLAM](https://mlsanity.com/paper/2112.12130/) (2021)
- [End-to-End Human Pose and Mesh Reconstruction with Transformers](https://mlsanity.com/paper/2012.09760/) (2020)
- [Cross-view Transformers for real-time Map-view Semantic Segmentation](https://mlsanity.com/paper/2205.02833/) (2022)
- [FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras](https://mlsanity.com/paper/2104.10490/) (2021)
- [CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers](https://mlsanity.com/paper/2207.02202/) (2022)
- [Atlas: End-to-End 3D Scene Reconstruction from Posed Images](https://mlsanity.com/paper/2003.10432/) (2020)
- [Orthographic Feature Transform for Monocular 3D Object Detection](https://mlsanity.com/paper/1811.08188/) (2018)
- [Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks](https://mlsanity.com/paper/2003.13402/) (2020)
- [DaViT: Dual Attention Vision Transformers](https://mlsanity.com/paper/2204.03645/) (2022)
- [Cross-view Semantic Segmentation for Sensing Surroundings](https://mlsanity.com/paper/1906.03560/) (2019)
- [Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks](https://mlsanity.com/paper/1804.02176/) (2018)
- [Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer](https://mlsanity.com/paper/2206.04584/) (2022)
- [Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmap](https://mlsanity.com/paper/2205.07002/) (2022)
- [Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving](https://mlsanity.com/paper/2210.08061/) (2022)
- [Dynamic 3D Scene Analysis by Point Cloud Accumulation](https://mlsanity.com/paper/2207.12394/) (2022)
- [Learning to Look around Objects for Top-View Representations of Outdoor Scenes](https://mlsanity.com/paper/1803.10870/) (2018)
- [A Geometric Approach to Obtain a Bird's Eye View from an Image](https://mlsanity.com/paper/1905.02231/) (2019)
- [Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation](https://mlsanity.com/paper/2110.11062/) (2021)

## Built on by (most cited first, 7 of 7)

- [CoBEV: Elevating Roadside 3D Object Detection with Depth and Height Complementarity](https://mlsanity.com/paper/2310.02815/) (2023)
- [DTCLMapper: Dual Temporal Consistent Learning for Vectorized HD Map Construction](https://mlsanity.com/paper/2405.05518/) (2024)
- [OE-BevSeg: An Object Informed and Environment Aware Multimodal Framework for Bird's-eye-view Vehicle Semantic Segmentation](https://mlsanity.com/paper/2407.13137/) (2024)
- [HierDAMap: Towards Universal Domain Adaptive BEV Mapping via Hierarchical Perspective Priors](https://mlsanity.com/paper/2503.06821/) (2025)
- [BEVUDA++: Geometric-aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2509.14151/) (2025)
- [OccLE: Label-Efficient 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2505.20617/) (2025)
- [DSOcc: Leveraging Depth Awareness and Semantic Aid to Boost Camera-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2505.20951/) (2025)

## Abstract (arXiv)

As bird's-eye-view (BEV) semantic segmentation is simple-to-visualize and easy-to-handle, it has been applied in autonomous driving to provide the surrounding information to downstream tasks. Inferring BEV semantic segmentation conditioned on multi-camera-view images is a popular scheme in the community as cheap devices and real-time processing. The recent work implemented this task by learning the content and position relationship via the vision Transformer (ViT). However, the quadratic complexity of ViT confines the relationship learning only in the latent layer, leaving the scale gap to impede the representation of fine-grained objects. And their plain fusion method of multi-view features does not conform to the information absorption intention in representing BEV features. To tackle these issues, we propose a novel cross-scale hierarchical Transformer with correspondence-augmented attention for semantic segmentation inferring. Specifically, we devise a hierarchical framework to refine the BEV feature representation, where the last size is only half of the final segmentation. To save the computation increase caused by this hierarchical framework, we exploit the cross-scale Transformer to learn feature relationships in a reversed-aligning way, and leverage the residual connection of BEV features to facilitate information transmission between scales. We propose correspondence-augmented attention to distinguish conducive and inconducive correspondences. It is implemented in a simple yet effective way, amplifying attention scores before the Softmax operation, so that the position-view-related and the position-view-disrelated attention scores are highlighted and suppressed. Extensive experiments demonstrate that our method has state-of-the-art performance in inferring BEV semantic segmentation conditioned on multi-camera-view images.