Papers › HSPFormer: Hierarchical Spatial Perception Transformer for Semantic Segmentation

HSPFormer: Hierarchical Spatial Perception Transformer for Semantic Segmentation

16 Jan 2025IEEE Transactions on Intelligent Transportation Systems 2025 1archive 2025-07-28

Siyu Chen, Ting Han, Changshe Zhang, Jinhe Su, Ruisheng Wang, Yiping Chen, Zongyue Wang, Guorong Cai

Semantic perception in driving scenarios plays a crucial role in intelligent transportation systems. However, existing Transformer-based semantic segmentation methods often do not fully exploit their potential in understanding driving scene dynamically. These methods typically lack spatial reasoning, failing to effectively correlate image pixels with their spatial positions, leading to attention drift. To address this issue, we propose a novel architecture, the Hierarchical Spatial Perception Transformer (HSPFormer), which integrates monocular depth estimation and semantic segmentation into a unified framework for the first time. We introduce the Spatial Depth Perception Auxiliary Network (SDPNet), a framework for multiscale feature extraction and multilayer depth map prediction to establish hierarchical spatial coherence. Additionally, we design the Hierarchical Pyramid Transformer Network (HPTNet), which uses depth estimation as learnable position embeddings to form spatially correlated semantic representations and generate global contextual information. Experiments on benchmark datasets such as KITTI-360, Cityscapes, and NYU Depth V2, demonstrate that HSPFormer outperforms several state-of-the-art networks, and achieves promising performance with 66.82% top-1 mIoU on KITTI-360, 83.8% mIoU on Cityscapes, and 57.7% mIoU on NYU Depth V2, respectively. The code will be made publicly available at https://github.com/SY-Ch/HSPFormer.

Paper PDF Code

Code

SY-Ch/HSPFormer mentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Depth Estimation Monocular Depth Estimation Semantic Segmentation Spatial Reasoning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Semantic Segmentation	KITTI-360	HSPFormer-DBS(RGB-Depth)	mIoU	67.32	#3 of 17	Archive leaderboard	report
Semantic Segmentation	KITTI-360	HSPFormer-UFS(RGB)	mIoU	66.82	#4 of 17	Archive leaderboard	report
Semantic Segmentation	NYU Depth v2	HSPFormer(PVT v2-B4)	Mean IoU	57.8%	#13 of 121	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections