Energy Ring: Stabilizing Feature Energy for Reliable Test-Time Discovery

Tianle Liu; Fan Lyu; Tingliang Feng; Chenggong Ni; Tianqi Wang; Zhang Zhang; Fuyuan Hu; Rui Yao

cs.AIOct 10, 2026

Energy Ring: Stabilizing Feature Energy for Reliable Test-Time Discovery

Authors: Tianle Liu, Fan Lyu, Tingliang Feng, Chenggong Ni, Tianqi Wang, Zhang Zhang, Fuyuan Hu, Rui Yao,

Organizations: School of Electronics and Information Engineering, Suzhou University of Science and Technology · Computer Vision Center, Universitat Autònoma de Barcelona · College of Computer Science, Northwest University · School of Intelligence Science and Technology, Nanjing University ·

Abstract

Test-Time Discovery (TTD) aims to recognize known classes and detect novel ones while the model is already deployed, operating directly on a continual unlabeled test-time stream. Existing TTD methods are overly conservative, making known and unknown features collapse together and difficult to separate during test-time adaptation. In this paper, we revisit TTD from an energy perspective and find that the natural energy gap between known and unknown classes is unstable and easily collapses. We therefore propose Energy Ring to stabilize this gap by anchoring the two types of classes on separate energy rings. A lightweight adapter enlarges the norm-based gap while preserving known-class directions, and a perturbation consistency module forms compact clusters for unknown classes. During testing, energy-guided confidence weighting improves prediction, and a stability-based rectification mechanism corrects unreliable updates. Experimental results show that Energy Ring significantly improves TTD performance against existing TTD methods.

Figures & tables

Figure 1: Energy comparisons among existing TTD methods and our method. HM keeps the backbone frozen and classifies based on fixed spatial energy. DAA collapses the original energy intensity onto a single hypersphere. Energy Ring compresses known and unknown classes onto different energy rings, yielding spatial-energy difference and retaining separability.

Figure 2: Task setting of TTD. In TTD, a model is pretrained on data containing only known classes. During deployment, the test data may include both known and unknown classes, requiring the model to predict known classes and discover novel ones.

Figure 3: Comparison of norm and angular prediction for test samples. Our method further expands the differences of energy in both intensity and direction.

Figure 4: Method Schema. ERA projects features onto concentric energy rings: high-energy ring for known classes and low-energy ring for unknowns, together with perturbation-consistency during training. During testing, we conduct energy-weighted prediction, while selectively rectifying high-perturbation samples to refresh memory queues and update ERA to rectify energy rings.

	Method	Real-time Evaluation			Post Evaluation
	Method	KA $\uparrow$	TA $\uparrow$	CA $\uparrow$	KA $\uparrow$	TA $\uparrow$	CA $\uparrow$	KF $\downarrow$
CIFAR100D	L2P ( Wang et al., 2022b )	59.93±2.15	8.57±2.49	43.10±4.30	50.53±7.25	9.60±1.50	27.39±2.11	27.85±7.21
	DP ( Wang et al., 2022a )	66.09±1.01	8.80±1.69	48.34 ±6.78	56.19±2.00	8.68±2.06	28.93±2.25	29.06±1.99
	GMP ( Cendra et al., 2024 )	72.77±1.20	7.37±0.88	42.26±4.54	67.21±2.53	13.04±2.59	27.10±1.77	17.69±2.53
	PHE ( Zheng et al., 2024 )	72.35±1.12	16.74±1.05	37.34±1.31	70.12±1.07	14.55± 1.01	24.65±1.35	2.12 ±0.92
	HM ( Lyu et al., 2025b )	79.17± 0.13	21.13± 0.62	56.37 ±1.42	80.73 ±1.59	31.03±1.24	34.81± 1.22	3.41 ±1.49

Table 1: Comparisons on four datasets. Real-time evaluation reflects the accumulated performance across all test batches, while post evaluation reassesses all test samples after testing. Bold and underlining denote the best and second-best results.

Method	CIFAR100D				CUB200D				T-ImageNetD				AircraftD
Method	HCA	ARI	NMI	VM	HCA	ARI	NMI	VM	HCA	ARI	NMI	VM	HCA	ARI	NMI	VM
HM ( Lyu et al., 2025b )	63.69	48.35	73.08	73.08	50.46	27.81	70.25	70.25	56.64	40.35	72.70	72.70	33.30	21.33	46.46	46.46
DAA ( Liu et al., 2025 )	65.62	53.96	75.20	75.21	58.19	32.43	75.29	75.29	58.91	42.50	73.53	73.53	32.08	21.20	46.44	46.44
Ours	66.38	53.54	75.36	75.36	58.34	33.70	75.53	75.53	58.25	43.26	73.36	73.36	33.21	22.13	47.02	47.02

Table 2: Comparisons of clustering metrics of post evaluation on four datasets.

Figure 5: Comparison on balance of Real-time TA and CA. Perfect Balance represents the most balanced TA and CA (TA = CA).

Table 8

Figure 8: T-SNE visualization in angular space on CIFAR100D with 5 known and 5 unknown classes.

Figure 9: Matching comparison between unknown class predictions and ground truth across methods on CIFAR-100D (90+10). Black rectangles indicate old class samples misclassified as unknowns.

Continual Test-Time Adaptation

Continual test-time adaptation updates pretrained models on unlabeled, changing deployment data while retaining useful knowledge across shifts.

See all 72 papers

EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems
May 2, 2025Xiao Ma, Young D. Kwon, Dong MaTest-Time Adaptation Continual Test-Time Adaptation
Singapore Management University, Singapore · Samsung AI Center–Cambridge, United Kingdom · University of Cambridge, United Kingdom
Private and Stable Test-Time Adaptation with Differential Privacy
Jun 1, 2026Zefeng Li, Qiaoyue Tang, Mathias Lecuyer +1Continual Test-Time Adaptation Privacy-Preserving ML
University of British Columbia · Vector Institute
TestDG: Test-time Domain Generalization for Continual Test-time Adaptation
Apr 7, 2025Sohyun Lee, Nayeong Kim, Juwon Kang +2Continual Test-Time Adaptation Cross-Domain Generalization
POSTECH · GenGenAI · KAIST AI

May 2, 2025J/K move · Enter open · S save

EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems

Xiao Ma, Young D. Kwon, Dong Ma

Singapore Management University, Singapore · Samsung AI Center–Cambridge, United Kingdom · University of Cambridge, United Kingdom

Test-Time Adaptation Continual Test-Time Adaptation On-Device Training Distribution Shift Detection

Open paper AskPDF arXiv

Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poor real-world applicability on resource-constrained edge devices, due to the substantial memory overhead and energy consumption. In this work, we first introduce a novel paradigm -- on-demand TTA -- which triggers adaptation only when a significant domain shift is detected. Then, we present OD-TTA, an on-demand TTA framework for accurate and efficient adaptation on edge devices. OD-TTA comprises three innovative techniques: 1) a lightweight domain shift detection mechanism to activate TTA only when it is needed, drastically reducing the overall computation overhead, 2) a source domain selection module that chooses an appropriate source model for adaptation, ensuring high and robust accuracy, 3) a decoupled Batch Normalization (BN) update scheme to enable memory-efficient adaptation with small batch sizes. Extensive experiments show that OD-TTA achieves comparable and even better performance while reducing the energy and computation overhead remarkably, making TTA a practical reality.

Abstract

Continual Test-Time Adaptation

Explore similar work

EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems

Private and Stable Test-Time Adaptation with Differential Privacy

TestDG: Test-time Domain Generalization for Continual Test-time Adaptation