Papers › Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation

Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation

1 Jul 2023arXiv:2307.00371archive 2025-07-28

Qi Bi, ShaoDi You, Theo Gevers

Domain-generalized urban-scene semantic segmentation (USSS) aims to learn generalized semantic predictions across diverse urban-scene styles. Unlike domain gap challenges, USSS is unique in that the semantic categories are often similar in different urban scenes, while the styles can vary significantly due to changes in urban landscapes, weather conditions, lighting, and other factors. Existing approaches typically rely on convolutional neural networks (CNNs) to learn the content of urban scenes. In this paper, we propose a Content-enhanced Mask TransFormer (CMFormer) for domain-generalized USSS. The main idea is to enhance the focus of the fundamental component, the mask attention mechanism, in Transformer segmentation models on content information. To achieve this, we introduce a novel content-enhanced mask attention mechanism. It learns mask queries from both the image feature and its down-sampled counterpart, as lower-resolution image features usually contain more robust content information and are less sensitive to style variations. These features are fused into a Transformer decoder and integrated into a multi-resolution content-enhanced mask attention learning scheme. Extensive experiments conducted on various domain-generalized urban-scene segmentation datasets demonstrate that the proposed CMFormer significantly outperforms existing CNN-based methods for domain-generalized semantic segmentation, achieving improvements of up to 14.00\% in terms of mIoU (mean intersection over union). The source code is publicly available at \url{https://github.com/BiQiWHU/CMFormer}.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

BiQiWHU/CMFormer officialmentioned in paperpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready 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

Decoder Domain Adaptation Domain Generalization Scene Segmentation Segmentation Semantic Segmentation Source-Free Domain Adaptation Synthetic-to-Real Translation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Domain Adaptation	Cityscapes to ACDC	CMFormer	mIoU	60.1	#10 of 16	Archive leaderboard	report
Domain Generalization	GTA-to-Avg(Cityscapes,BDD,Mapillary)	CMFormer	mIoU	51.10	#13 of 24	Archive leaderboard	report
Domain Generalization	GTA5-to-Cityscapes	CMFormer	mIoU	55.31	#6 of 8	Archive leaderboard	report
Semantic Segmentation	GTAV-to-Cityscapes Labels	CMFormer	mIoU	55.3	#11 of 12	Archive leaderboard	report
Source-Free Domain Adaptation	Cityscapes to ACDC	CMFormer	mIoU	60.1	#2 of 2	Archive leaderboard	report
Synthetic-to-Real Translation	GTAV-to-Cityscapes Labels	CMFormer	mIoU	59.7	#20 of 73	Archive leaderboard	report
Synthetic-to-Real Translation	SYNTHIA-to-Cityscapes Labels	CMFormer	mIOU	44.6	#2 of 2	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 Focus 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