DA-Mamba: Learning Domain-Aware State Space Model for Global-Local Alignment in Domain Adaptive Object Detection

Haochen Li; Rui Zhang; Hantao Yao; Xin Zhang; Yifan Hao; Shaohui Peng; Yongwei Zhao; Ling Li

cs.CVMar 19, 2026

DA-Mamba: Learning Domain-Aware State Space Model for Global-Local Alignment in Domain Adaptive Object Detection

Authors: Haochen Li, Rui Zhang, Hantao Yao, Xin Zhang, Yifan Hao, Shaohui Peng, Yongwei Zhao, Ling Li

Organizations: Intelligent Software Research Center, Institute of Software, CAS · University of Chinese Academy of Sciences · State Key Lab of Processors, Institute of Computing Technology, CAS · School of Information Science and Technology, University of Science and Technology of China

Abstract

Domain Adaptive Object Detection (DAOD) aims to transfer detectors from a labeled source domain to an unlabeled target domain. Existing DAOD methods employ multi-granularity feature alignment to learn domain-invariant representations. However, the local connectivity of their CNN-based backbone and detection head restricts alignment to local regions, failing to extract global domain-invariant features. Although transformer-based DAOD methods capture global dependencies via attention mechanisms, their quadratic computational cost hinders practical deployment. To solve this, we propose DA-Mamba, a hybrid CNN-State Space Models (SSMs) architecture that combines the efficiency of CNNs with the linear-time long-range modeling capability of State Space Models (SSMs) to capture both global and local domain-invariant features. Specifically, we introduce two novel modules: Image-Aware SSM (IA-SSM) and Object-Aware SSM (OA-SSM). IA-SSM is integrated into the backbone to enhance global domain awareness, enabling image-level global and local alignment. OA-SSM is inserted into the detection head to model spatial and semantic dependencies among objects, enhancing instance-level alignment. Comprehensive experiments demonstrate that the proposed method can efficiently improve the cross-domain performance of the object detector.

Figures & tables

Figure 1: (a) Existing DAOD methods focus on aligning features at image and instance-level to extract domain-invariant features. However, they only achieve local alignment due to the locality of CNN-based backbone and head, resulting in insufficient alignment across regions. (b) Our DA-Mamba utilizes SSM’s long-range perception capability to extract global domain-invariant features, introducing the Image-Aware SSM module to the backbone to supplement global domain attributes, and the Object-Aware SSM module to the detection head to model spatial and semantic dependencies between objects, achieving fine-grained alignment at image and instance-level.

Figure 2: Overview of the proposed DA-Mamba. The proposed IA-SSM and OA-SSM are integrated into the FPN of the backbone and detection head, respectively, providing fine-grained image and instance-level global-local alignment.

Figure 3: The architecture of (a) Mamba layer [ 22 ] (b) Image-Aware SSM module and (c) Object-Aware SSM module.

		C $\rightarrow$ F
Methods	Venue	Person	Rider	Car	Truck	Bus	Train	Motor	Bicycle	mAP
DA-Faster [ 7 ]	CVPR 2018	29.2	40.4	43.4	19.7	38.3	28.5	23.7	32.7	32.0
LRA [ 51 ]	TNNLS 2024	45.6	47.1	59.7	31.2	52.4	44.6	28.1	39.5	43.5
SIGMA++ [ 43 ]	TPAMI 2023	46.4	45.1	61.0	32.1	52.2	44.6	34.8	39.9	44.5
FA-TDCA [ 47 ]	TNNLS 2025	43.5	51.7	58.8	34.1	52.6	40.4	36.0	42.3	44.9
MTM [ 61 ]	AAAI 2024	51.0	53.4	67.2	37.2	54.4	41.6	38.4	47.7	48.9

Table 1: Comparison (

\%

) on Cross-Weather adaptation task Cityscapes

\rightarrow

Foggy Cityscapes (C

\rightarrow

	C $\rightarrow$ B								P $\rightarrow$ Cmc
Methods	Person	Rider	Car	Truck	Bus	Motor	Bicycle	mAP	Bicycle	Bird	Car	Cat	Dog	Person	mAP
DA-Faster [ 7 ]	28.9	27.4	44.2	19.1	18.0	14.2	22.4	24.9	-	-	-	-	-	-	-
SWDA [ 53 ]	30.2	29.5	45.7	15.2	18.4	17.1	21.2	25.3	36.0	18.3	29.3	9.3	22.9	48.4	27.4
DBGL [ 3 ]	-	-	-	-	-	-	-	-	35.6	20.3	33.9	16.4	26.6	45.3	29.7
FGRR [ 4 ]	-	-	-	-	-	-	-	-	42.2	21.1	30.2	21.9	30.0	51.5	32.7
SFA [ 60 ]	40.2	27.6	57.5	19.1	23.4	15.4	19.2	28.9	-	-	-	-	-	-	-

Table 2: Comparison (

\%

) on Cross-FOV adaptation task Cityscapes

\rightarrow

BDD100K (C

\rightarrow

B) and Cross-Style adaptation task Pascal VOC

\rightarrow

Comic (P

\rightarrow

Cmc)

Methods	Aero	Bike	Bird	Boat	Bottle	Bus	Car	Cat	Chair	Cow	Table	Dog	Horse	Motor	Person	Plant	Sheep	Sofa	Train	Tv	mAP
UaDAN [ 24 ]	35.0	73.7	41.0	24.4	21.3	69.8	53.5	2.3	34.2	61.2	31.0	29.5	47.9	63.6	62.2	61.3	13.9	7.6	48.6	23.9	40.2
TFD [ 59 ]	27.9	64.8	28.4	29.5	25.7	64.2	47.7	13.5	47.5	50.9	50.8	21.3	33.9	60.2	65.6	42.5	15.1	40.5	45.5	48.6	41.2
UMT [ 13 ]	39.6	59.1	32.4	35.0	45.1	61.9	48.4	7.5	46.0	67.6	21.4	29.5	48.2	75.9	70.5	56.7	25.9	28.9	39.4	43.6	44.1
ATMT [ 41 ]	37.5	63.4	37.9	29.8	45.1	62.7	41.2	19.5	43.7	57.4	22.9	25.3	39.6	87.1	70.9	50.6	29.1	32.2	58.4	50.5	45.2
CIGAR [ 46 ]	35.2	55.0	39.2	30.7	60.1	58.1	46.9	31.8	47.0	61.0	21.8	26.7	44.6	52.4	68.5	54.4	31.3	38.8	56.5	63.5	46.2
TIA [ 64 ]	42.2	66.0	36.9	37.3	43.7	71.8	49.7	18.2	44.9	58.9	18.2	29.1	40.7	87.8	67.4	49.7	27.4	27.8	57.1	50.6	46.3

Table 3: Comparison (

\%

) on Cross-Style adaptation task Pascal VOC

\rightarrow

Clipart (P

\rightarrow

Clp)

Method	C $\rightarrow$ F	C $\rightarrow$ B	P $\rightarrow$ Clp	P $\rightarrow$ Cmc
w/o	52.3	41.9	46.8	37.9
w/ IA-SSM	56.8(+4.5)	45.9(+4.0)	50.6(+3.8)	40.5(+2.6)
w/ OA-SSM	55.4(+3.1)	45.0(+3.1)	50.5(+3.7)	40.6(+2.7)
w/ both	58.1(+5.8)	48.7(+6.8)	52.5(+5.7)	43.8(+5.9)

Table 4: Ablation (

\%

) on DA-Mamba.

Component	Method	C $\rightarrow$ F	C $\rightarrow$ B	P $\rightarrow$ Clp	P $\rightarrow$ Cmc
Backbone	Mamba [ 49 ]	54.3	43.4	48.3	38.7
Backbone	IA-SSM	56.8	45.9	50.6	40.5
Head	Mamba [ 49 ]	53.4	43.3	47.6	38.4
Head	OA-SSM	55.4	45.0	50.5	40.6
Backbone+Head	Mamba [ 49 ]	55.0	44.8	48.7	38.9
Backbone+Head	DA-Mamba	58.1	48.7	52.5	43.8

Table 5: Comparison (

\%

) with standard Mamba.

Method	Arch.	Inference Mem. Usg.	FPS	Training Mem. Usg.	Training s/iter	FLOPs	mAP	Abs. Gains
DA-Pro [ 38 ]	Visual-Language Model	2549M	2.5	4034M	1.472S	243G	55.9	3.3
DATR [ 5 ]	Transformer-based Attention	3206M	5.8	21606M	0.906s	279G	53.4	5.3
Baseline	CNN-based Backbone	1190M	15.2	14581M	0.703s	140G	52.3	-
Baseline+GC Block	CNN-based Attention	1341M	14.1	15238M	0.776s	146G	54.1	1.8
Baseline+ViT Block	Transformer-based Attention	2090M	10.6	19322M	0.862s	208G	57.5	5.2
Baseline+Mamba Block	SSM-based Attention	1792M	13.0	18027M	0.799s	182G	55.0	2.7

Table 6: Comparison (

\%

) of computational overhead.

Conv	SSM	Prompts	C $\rightarrow$ F	C $\rightarrow$ B	P $\rightarrow$ Clp	P $\rightarrow$ Cmc
			52.3	41.9	46.8	37.9
✓			53.5	43.8	47.6	38.3
	✓		54.3	43,4	48.3	38.7
✓	✓		55.6	45.0	49.2	40.0
✓		✓	53.9	44.0	48.3	38.4
	✓	✓	54.9	43.9	49.0	40.0

Table 7: Ablation (

\%

) on IA-SSM.

Conv	SSM	Prompts	C $\rightarrow$ F	C $\rightarrow$ B	P $\rightarrow$ Clp	P $\rightarrow$ Cmc
			52.3	41.9	46.8	37.9
✓			53.2	43.2	47.5	38.1
	✓		53.4	43.3	47.6	38.4
✓	✓		54.8	44.6	49.4	39.8
✓		✓	53.8	43.3	47.8	38.5
	✓	✓	54.5	44.0	48.7	39.2

Table 8: Ablation (

\%

) on OA-SSM.

IA-SSM			mAP	OA-SSM			mAP
C3	C4	C5	mAP	P3	P4	P5	mAP
			52.3				52.3
✓			53.8	✓			53.9
	✓		54.0		✓		53.9
		✓	54.3			✓	54.1

Table 9: Ablation studies (

\%

) for insertion sites of DA-Mamba.

Benchmark	Category	Baseline (UDA)	DA-Mamba	Gains
C $\rightarrow$ F	8	52.3	58.1	5.8
C $\rightarrow$ B	7	41.9	48.7	6.8
P $\rightarrow$ Clp	20	46.2	52.5	6.3
P $\rightarrow$ Cmc	6	37.9	43.8	5.9
K $\rightarrow$ C	1	60.4	62.5	3.1
S $\rightarrow$ C	1	59.3	62.3	3.0

Table 10: Comparison (

\%

) on benchmarks with various categories.

Figure 4: Different structure for IA-SSM and OA-SSM.

Structure	Param(M)	FPS	mAP
Serial	8.610	12.6	58.1
Parallel	1.732	14.1	58.1

Table 11: Comparison (

\%

) of different SSM structure.

Figure 5: Visualizations of the extracted feature map.

Figure 6: Visualizations of the similarity between the features of a certain point and other regions on the feature map.

Figure 7: T-SNE visualization of the features extracted from the target domain.

Figure 8: T-SNE visualization of the features extracted from both domains.

Figure 9: Detection results visualization.

Benchmark	Pseudo Labels	C $\rightarrow$ F	C $\rightarrow$ B	P $\rightarrow$ Clp	P $\rightarrow$ Cmc
Baseline(UDA)		50.6	40.0	43.8	35.9
Baseline(UDA)	$\checkmark$	52.3	41.9	46.2	37.9
DA-Mamba		57.1	48.0	51.0	42.5
DA-Mamba	$\checkmark$	58.1	48.7	52.5	43.8

Table 12: Analysis (

\%

) on Pseudo Labels.

C $\rightarrow$ F	C $\rightarrow$ B	P $\rightarrow$ Clp	P $\rightarrow$ Cmc
58.1( $\pm$ 0.2)	48.7( $\pm$ 0.4)	52.5( $\pm$ 0.3)	43.8( $\pm$ 0.4)

Table 13: mAP(

\%

) on four benchmarks.

Object Detection

Object detection locates and classifies objects in images or video, balancing localization accuracy, robustness, and inference speed.

See all 624 papers

CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object Detection
Feb 26, 2026Boyang Dai, Zeng Fan, Zihao Qi +2Object Detection Source-Free Domain Adaptation
School of Computing and Data Science, The University of Hong Kong · Department of Electrical & Computer Engineering, National University of Singapore · School of Information and Electronics, Beijing Institute of Technology
Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection
Apr 9, 2026Jun Li, Yingying Shi, Zhixuan Ruan +2Object Detection Visual SSMs
School of Computer and Electronic Information, Nanjing Normal University, 210023, China
JMT-YOLO: Multi-task Domain Adaptation via Segmentation-Guided Consistency Learning
Oct 9, 2026Zhenhua Yu, Jiahao Zhang, Wenchao Zhang +2Object Detection Unsupervised Domain Adaptation
Institute of Systems Security and Control, College of Artificial Intelligence and Computer Science, Xi’an University of Science and Technology, Xi’an 710054, China

Feb 26, 2026J/K move · Enter open · S save

CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object Detection

Boyang Dai, Zeng Fan, Zihao Qi, Meng Lou+1

School of Computing and Data Science, The University of Hong Kong · Department of Electrical & Computer Engineering, National University of Singapore · School of Information and Electronics, Beijing Institute of Technology

Object Detection Source-Free Domain Adaptation Object-Centric Representation Learning Slot Attention

Open paper AskPDF arXiv

Source-Free Domain Adaptive Object Detection (SF-DAOD) aims to adapt a detector trained on a labeled source domain to an unlabeled target domain without retaining any source data. Despite recent progress, most popular approaches focus on tuning pseudo-label thresholds or refining the teacher-student framework, while overlooking object-level structural cues within cross-domain data. In this work, we present CGSA, the first framework that brings Object-Centric Learning (OCL) into SF-DAOD by integrating slot-aware adaptation into the DETR-based detector. Specifically, our approach integrates a Hierarchical Slot Awareness (HSA) module into the detector to progressively disentangle images into slot representations that act as visual priors. These slots are then guided toward class semantics via a Class-Guided Slot Contrast (CGSC) module, maintaining semantic consistency and prompting domain-invariant adaptation. Extensive experiments on multiple cross-domain datasets demonstrate that our approach outperforms previous SF-DAOD methods, with theoretical derivations and experimental analysis further demonstrating the effectiveness of the proposed components and the framework, thereby indicating the promise of object-centric design in privacy-sensitive adaptation scenarios. Code is released at https://github.com/Michael-McQueen/CGSA.

Abstract

Object Detection

Explore similar work

CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object Detection

Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection

JMT-YOLO: Multi-task Domain Adaptation via Segmentation-Guided Consistency Learning