TC-ADA: One-Shot Active Domain Adaptation for Semantic Segmentation

Weihao Yan; Yeqiang Qian; Yueyuan Li; Tao Li; Chunxiang Wang; Ming Yang

cs.CVSep 27, 2026

TC-ADA: One-Shot Active Domain Adaptation for Semantic Segmentation

Authors: Weihao Yan, Yeqiang Qian, Yueyuan Li, Tao Li, Chunxiang Wang, Ming Yang

Organizations: School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai, 200240, China

Abstract

Manual dense annotation remains a major obstacle to deploying semantic segmentation models in new driving environments. Active domain adaptation (ADA) seeks label-efficient transfer by annotating only a selected portion of the target domain. Existing ADA methods commonly implement this process through multiple rounds of acquisition, annotation, and retraining. We study a practical one-shot image-level setting that selects and densely annotates a fixed target subset in a single round, followed by uninterrupted adaptation. Within this setting, we develop Target-Calibrated Active Domain Adaptation (TC-ADA) as a joint design of complete-image acquisition and target-calibrated adaptation. Stage1 uses visual representations from a vision foundation model (VFM) together with semantic predictions from a fixed unsupervised domain adaptation model to select representative and informative target images without target annotations. Stage2 jointly uses labeled source data, labeled target data, and the remaining unlabeled target data, while calibrating source and target supervision under limited target labels. Extensive experiments across five synthetic-to-real and real-to-real driving transfers show consistent improvements over representative ADA baselines. With only 23 to 46 labeled target images on four transfers and 140 on Mapillary, TC-ADA stays within 1.9 mean intersection over union (mIoU) points of target-only full supervision. Code will be available at https://github.com/ywher/TC-ADA.

Figures & tables

Fig. 1: Motivation and protocol overview of TC-ADA. It replaces iterative acquisition–annotation–retraining cycles with a single complete-image annotation round followed by uninterrupted adaptation. TC-ADA reaches 77.66% mean intersection over union (mIoU) using only 25 of 1,600 ACDC target images, close to the 77.72% full-supervision reference.

Fig. 2: Overview of TC-ADA. Stage 1 ranks complete target images using perspective-aware VFM features, density–diversity coverage, and reliable rare-class evidence. Stage 2 combines source and target supervision through two mixed branches, with budget-aware target-supervision attenuation, target-dominant mixing, and target-aware initialization. Distillation and progressive acquisition are optional extensions.

Shift	Transfer	Cls.	#Source	#Target	#Val
S2R	GTA $\rightarrow$ Cityscapes	19	24,966	2,975	500
S2R	SYNTHIA $\rightarrow$ Cityscapes	16	9,400	2,975	500
R2R	Cityscapes $\rightarrow$ ACDC	19	2,975	1,600	406
	Cityscapes $\rightarrow$ MUSES	19	2,975	1,500	250
	Cityscapes $\rightarrow$ Mapillary	19	2,975	18,000	2,000

TABLE I: Driving adaptation datasets and split sizes.

Method

Type

Segmentor

Params (M)

Train. (M)

Src. data

Tgt. data

Annotation unit

Annot. rounds

G2C

S2C

C2A

C2Mu

C2Map

Avg.

1/64 (46)

1/64 (25)

1/64 (23)

1/128 (140)

Full-data references (HRDA/DINOv3-B)

Target full

Ref.

HRDA/DINOv3-B

92.31

6.64

–

\checkmark

Image

–

82.49

82.81

77.72

79.25

80.04

80.46

Source+target full

Ref.

HRDA/DINOv3-B

92.31

6.64

\checkmark

\checkmark

Image

–

81.77

82.50

78.26

80.72

80.44

80.74

Native-protocol reproductions

AllSpark [ 31 ]

Semi

SegFormer/MiT-B5

84.61

–

\checkmark

Image

62.57

68.11

44.67

31.51

66.76

54.72

TABLE II: Protocol-aware comparison at the lowest target-label budgets (mIoU, %). Parentheses give labeled-image counts for image-level protocols.

Method	Segmentor	100	200	500	1000
GTA $\rightarrow$ Cityscapes-19		Target full: 82.5
SemiDAViL [ 41 ] $\dagger$	CLIP-B/16+DLG	71.1	72.5	72.9	74.8
TC-ADA	HRDA/DINOv3-B	81.1	81.4	82.6	82.6
Gain	–	+10.0	+8.9	+9.7	+7.8
SYNTHIA $\rightarrow$ Cityscapes-16		Target full: 82.8
SemiDAViL [ 41 ] $\dagger$	CLIP-B/16+DLG	76.9	77.2	78.6	79.7

TABLE III: Supplementary fixed-count Cityscapes comparison (mIoU, %).

Method	Target-label budget
(a) GTA $\rightarrow$ Cityscapes-19 Synthetic-to-real; eval: val
Ratio (images)	1/64 (46)	1/32 (93)	1/16 (186)	1/8 (372)
UniMatchV2 [ 27 ]	72.65	76.95	80.17	80.95
UniMatchV2+Source [ 27 ]	75.86	78.41	79.17	80.10
HALO-Image [ 8 ]	73.00	74.27	76.39	77.47
MADAv2-HRDA [ 9 ]	76.27	77.66	78.82	79.60

TABLE IV: Image-level comparison across target-label budgets.

Layout	CN	1/64	1/16	Avg.	Storage $\downarrow$ (MiB)
Global	–	76.95	77.49	77.22	19
$+$ G2x2	yes	77.19	78.04	77.62	94
$+$ G4x4	yes	77.37	77.79	77.58	319
$+$ G4x8	yes	76.93	78.02	77.47	619
$+$ G8x8	yes	77.58	77.83	77.70	1219
$+$ G2x4	yes	77.66	78.08	77.87	169

TABLE V: Embedding-layout ablation on C2A with sampling fixed (mIoU, %).

Sampler	C2A			C2Map
Sampler	1/64	1/16	Avg.	1/128
Random	76.58	77.56	77.07	78.75
Uniform	77.14	77.83	77.48	79.01
Entropy	76.65	77.56	77.11	78.54
K-center [ 36 ]	77.27	77.57	77.42	78.09
Density-k-center [ 33 ]	77.17	77.69	77.43	78.90

TABLE VI: Comparison of Stage 1 sampling strategies (mIoU, %).

Panel of Figure 9 — Fig. 3: Qualitative comparison at the lowest budgets. From top to bottom: G2C/C2A/C2Mu at 1/64 and C2Map at 1/128. From left to right: input image, ground truth, HALO [ 8 ] , MADAv2 [ 9 ] , UniMatchV2 [ 27 ] , and TC-ADA.

Selection	Class entropy $\uparrow$		Rare enrich. $\uparrow$		Diversity $\uparrow$
Selection	1/64	1/16	1/64	1/16	1/64	1/16
Random	1.8351	1.8569	1.43	1.10	0.1352	0.1369
Uniform	1.8932	1.9046	1.93	1.44	0.1220	0.1432
Entropy	1.6971	1.7169	0.69	0.88	0.1309	0.1257
K-center [ 36 ]	1.9846	1.9957	3.11	2.42	0.1715	0.1546
Density-k-center [ 33 ]	1.8816	1.9695	1.67	2.07	0.1731	0.1528

TABLE VII: Semantic coverage and feature diversity of selected ACDC subsets.

Evidence	C2A		G2C		C2Map	C2Mu	$\Delta$ DKC
Evidence	1/64	1/16	1/64	1/16	1/128	1/16	$\Delta$ DKC
None (DKC)	77.17	77.69	80.21	81.20	78.90	78.28	0.00
Uncertainty	77.13	78.46	79.76	81.25	78.62	77.90	-0.13
Entropy	77.62	77.19	79.99	81.66	78.84	78.29	+0.01
Confidence	76.98	77.13	80.17	81.33	79.29	78.49	+0.07
Rare coverage (R)	77.66	78.08	80.64	81.24	79.20	79.40	+0.52

TABLE VIII: Individual semantic cues added separately to DKC with fixed G2x4 embeddings (mIoU, %).

Configuration	Area	Conf.	Rarity	1/64	1/16	Avg.
DKC baseline	–	–	–	77.17	77.69	77.43
w/o area scaling	–	$\checkmark$	$\checkmark$	77.46	77.67	77.57
w/o class confidence	$\checkmark$	–	$\checkmark$	76.78	77.93	77.36
w/o rarity weighting	$\checkmark$	$\checkmark$	–	77.73	77.82	77.78
Full R	$\checkmark$	$\checkmark$	$\checkmark$	77.66	78.08	77.87

TABLE IX: Internal components of reliable rare-class coverage on C2A (mIoU, %).

Method	Mode	Rounds	G2C 1/64		C2A 1/64		C2Map 1/128		Avg.
			mIoU	min	mIoU	min	mIoU	min	mIoU	min
RIPU-Image [ 6 ]	Online	5	74.57	93.7	66.00	53.5	75.43	738.0	72.00	295.1
D2ADA-Image [ 7 ]	Online	5	68.79	1095.5	65.82	232.4	70.85	381.9	68.49	569.9
HALO-Image [ 8 ]	Online	5	73.00	70.2	70.30	36.3	75.90	411.0	73.07	172.5
MADAv2-HRDA [ 9 ]	Offline	1	76.27	165.4	70.42	26.2	76.59	138.9	74.43	110.2
TC-ADA (R-DKC)	Offline	1	80.64	17.7	77.66	8.9	79.20	107.0	79.17	44.5

TABLE X: ADA accuracy (mIoU, %) and acquisition cost under matched image-level budgets.

Setting	Stage 2 design						Init.	C2A	G2C
Setting	$S\!\to\!T_{u}$	$S\!\to\!T_{l}$	T-Sup	T-Mix	Atten.	TDM	Init.	1/64	1/64
Target full supervision	–	–	–	–	–	–	–	77.72	82.49
Source only	–	–	–	–	–	–	–	70.32	69.79
DACS ( $S\!\to\!T_{u}$ )	$\checkmark$	–	–	–	–	–	scratch	72.92	77.13
$+$ labeled-target context	$\checkmark$	$\checkmark$	–	–	–	–	scratch	76.56	79.37
$+$ direct T-Sup	$\checkmark$	$\checkmark$	$\checkmark$	–	–	–	scratch	75.87	78.60

TABLE XI: Ablation of target-calibrated adaptation on C2A and G2C (mIoU, %).

Transfer	Budget	VFM encode	UDA stats	R-DKC ranking	Total
G2C	1/64	$2.93{\pm}0.07$	$14.57{\pm}0.02$	$0.23{\pm}0.00$	$17.72{\pm}0.09$
C2A	1/64	$1.21{\pm}0.16$	$7.53{\pm}0.04$	$0.13{\pm}0.01$	$8.87{\pm}0.19$
C2Map	1/128	$20.70{\pm}0.32$	$83.14{\pm}0.40$	$3.19{\pm}0.11$	$107.02{\pm}0.74$

TABLE XII: Breakdown of our one-shot acquisition time (minutes).

Method	Varied factor	G2C 1/64	C2A 1/64
Random	Selection seed	$80.07\pm 0.36$	$76.86\pm 0.33$
TC-ADA	Training seed	$80.55\pm 0.11$	$77.67\pm 0.09$

TABLE XIII: Three-run reliability at the lowest budget (mIoU, %; mean

\pm

sample standard deviation).

	G2C			S2C
Setting	1/64	1/32	1/16	1/64	1/32	1/16
One-shot	80.64	80.70	81.24	81.31	81.75	82.15
Progressive	80.49	81.25	81.67	81.38	81.91	82.36
$\Delta$	-0.15	+0.55	+0.43	+0.07	+0.16	+0.21
Avg. extra time (min)	23.2			27.7

TABLE XIV: Progressive acquisition on synthetic-to-real transfers (mIoU, %).

Model	Full sup	Sup@r	Semi@r	TC-ADA@r	$+$ KD
GTA $\rightarrow$ Cityscapes; $r=1/8$ ; target eval: val
DINOv3-L	83.88	81.88	83.39	83.55	–
DINOv2-B	82.47	79.88	81.54	82.15	–
PIDNet-S	75.59	67.74	71.96	72.80	74.45
Cityscapes $\rightarrow$ ACDC; $r=1/16$ ; target eval: val
DINOv3-L	80.27	76.34	78.73	80.44	–

TABLE XV: Generalization across segmentation models (mIoU, %).

Explore similar work

TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model
Jul 4, 2026Dimitrios Fotiou, Vasileios Mygdalis, Ioannis PitasDomain Adaptation Few-Shot Segmentation
Aristotle University of Thessaloniki
Dual-Foundation Models for Unsupervised Domain Adaptation
May 5, 2026Yerin Cheon, Aruna Balasubramanian, Francois RameauDomain Adaptation Semantic Segmentation
Stony Brook University, Stony Brook, NY, USA · SUNY Korea, The State University of New York, Korea
DOME: Learning Transferable Domain Variables from Sparse Supervision for Test-Time Adaptation
Jun 2, 2026Xiaoran Xu, Yifan Xu, Yupeng Wu +2Mitigating Domain Shift Sparse Supervision
MAIS, IACAS · Beijing, China

Jul 4, 2026, cs.CVJ/K move · Enter open · S save

TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model

Dimitrios Fotiou, Vasileios Mygdalis, Ioannis Pitas

Aristotle University of Thessaloniki

Domain Adaptation Few-Shot Segmentation Recent Vision Foundation Models

Open paper AskPDF arXiv

Test-Time Domain Adaptation (TTDA) aims to adapt Deep Neural Networks to distribution shifts using only streaming, unlabeled test data in real time. Current methods for semantic segmentation tasks suffer from critical limitations. Entropy minimization techniques require costly backpropagation, risking catastrophic forgetting and producing noisy segmentation boundaries. Memory-bank methods, while backpropagation-free, exhibit slow adaptation, requiring numerous samples to converge and struggle to handle continuous domain shifts. We introduce TestMate, a novel, real-time, and backpropagation-free TTDA framework that overcomes these issues. TestMate leverages generalization capability of a lightweight Visual Foundation Model to guide the adaptation. We use a zero-shot instance segmentation YOLOv8-seg based model to generate unlabeled mask proposals for objects and their parts at multiple scales in real time. These proposals are fused with the primary model via a heuristic, size-ordered competitive scheme, where small, high-confidence regions dominate and refine predictions in surrounding larger, less certain areas. This paremeter-free mechanism enables immediate adaptation from the first frame, inherently avoids catastrophic forgetting and effectively preserves fine object details and boundaries, even for small objects. TestMate can be used as a standalone, efficient refinement module or seamlessly integrated into existing TTDA methods to significantly boost their performance. We demonstrate state-of-the-art results across two benchmark datasets, proving TestMate's effectiveness in three distinct adaptation tasks: TTDA, Source-Free Domain Adaptation (SFDA), and online-TTDA. Code is available.

Abstract

Explore similar work

TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model

Dual-Foundation Models for Unsupervised Domain Adaptation

DOME: Learning Transferable Domain Variables from Sparse Supervision for Test-Time Adaptation