LUMIN: Lightweight Universal Manufacturing Inspection Network for Anomaly Detection

Pengfei Yang

cs.CVSep 4, 2026

LUMIN: Lightweight Universal Manufacturing Inspection Network for Anomaly Detection

Authors: Pengfei Yang

Organizations: Intelligent Precision Instrument, Shenzhen, Guangdong, China

Abstract

Industrial anomaly detection faces two engineering bottlenecks: memory bank construction latency and inference efficiency. Traditional sampling algorithms (Farthest Point Sampling, K-Means, etc.) rely on numerous backbone forward passes and iterative distance computations, with construction times ranging from minutes to hours; heavy computation components such as multi-scale feature extraction struggle to meet the millisecond-level real-time requirements of production lines. This paper focuses on sampling efficiency and inference optimization for industrial deployment with two core contributions: (1) PSP (Plugin Sampler Pipeline)---a four-stage adaptive memory bank sampling pipeline based on 18-dimensional pixel metadata and five complementary visual plugins. PSP completes all sampling with zero backbone forward passes; coarse filtering is sub-second numerical sorting, and metadata extraction is a one-time offline cost. PSP supports progressive deployment and incremental updates. (2) Two engineering optimization strategies---parallel memory bank similarity computation (reducing inference memory and latency by over 95%) and stratified pixel sampling for large-scale evaluation (reducing computation time by 20 $\times$ while keeping metrics stable). As a vehicle for validation, we introduce LUMIN (Lightweight Universal Manufacturing Inspection Network) with extreme segmentation-head compression, systematically exploring the accuracy-efficiency frontier against strong baselines. Experiments on five benchmarks demonstrate that PSP matches state-of-the-art sampling accuracy at near-random construction cost (341 $\times$ faster than FPS), while inference optimizations reduce evaluation time by 20 $\times$ with negligible accuracy loss.

Figures & tables

Fig. 1: Overall architecture of the LUMIN framework, including the training pipeline (left); the memory bank building pipeline (middle); and the inference pipeline (right).

Fig. 2: Detection head evolution. UniADet (left): dual-branch with classification and segmentation; UniADet_seg (middle): single-branch with classification head removed; LUMIN (right): single-layer segmentation head with cross-layer FeatFusion.

Component	UniADet	UniADet_seg	LUMIN
Fusion	(Post-) Scores	(Post-) Scores	(Pre-) Features
Segmentation Head	Multiple	Multiple	Single
Trainable Parameters	$\sim$ 16K ( $4LD$ )	$\sim$ 8K ( $2LD$ )	$\sim$ 2K ( $2D$ )
Size of .pth File	$\sim$ 72KB	$\sim$ 37KB	$\sim$ 11KB

TABLE I: Architecture evolution: comparison of UniADet, UniADet_seg, and LUMIN with

L=4

Category	D	Description
Basic attributes	3	width, height, aspect ratio
Color statistics	6	mean and standard deviation of RGB three channels
Gradient magnitude	3	Sobel gradient mean, standard deviation, P90 quantile
Local entropy	2	mean and standard deviation over 5 $\times$ 5 window
Frequency-domain energy	3	FFT low/mid/high-frequency energy ratios
Global contrast	1	RMS mean of RGB channel variances

TABLE II: Composition of the 18-dimensional (D) pixel metadata.

Rule	If	Then
R1	High RGB variance	$\uparrow$ ColorPlugin
R2	High gradient variance	$\uparrow$ TexturePlugin (HOG)
R3	High local entropy variance	$\uparrow$ TexturePlugin (LBP)
R4	High scale/contrast variance	$\uparrow$ ResizePatchPlugin
R5	High high-frequency energy	$\uparrow$ FrequencyPlugin
R6	High brightness dynamic range	$\uparrow$ ContrastPlugin

TABLE III: Adaptive decision rules for dynamic plugin weighting (

\uparrow

denotes increasing the corresponding plugin weight).

Parameter	Default	Stage	Description
work_size	256	Stage 1	Image resize resolution for metadata extraction. The 16–512 range has minimal impact on P-AUPR (fluctuation $<$ 0.2%); 256 balances efficiency and statistical stability.
coarse_keep_ratio	5.0	Stage 2	Retention ratio for coarse filtering: $K_{\text{coarse}}=\text{keep\_ratio}\times K$ . At $K=20$ , retains 100 candidates. Setting to 1.0 enables zero-overhead minimal sampling.
prior_strength	0.3	Stage 3	Fusion ratio between dataset prior and adaptive score; constrains adaptive weight fluctuation and improves cross-scenario stability.
n_clusters	0	Stage 4	Number of clustering constraints after fusion scoring. 0 disables clustering, selecting Top- $K$ directly by composite score for stable industrial scenarios.
manual_weights	None	Stage 3/4	Manually specified five-plugin fusion weights. If not None, overrides adaptive weights for on-demand plugin priority customization.

TABLE IV: Key hyperparameters of the PSP pipeline: default values, associated stages, and functional descriptions.

Datasets	Metrics	Anomaly -CLIP	VisualAD (CLIP)	UniADet (CLIP)	UniADet (DINOv3)	LUMIN (CLIP)	LUMIN (DINOv3)
MVTec	AUROC	72.6/78.0	88.1/89.8	89.7 / 90.0	91.6 / 90.4	56.3/78.6	87.4/89.3
MVTec	AUPR	86.8/ 77.8	94.8/40.1	95.2 /43.5	96.2 /46.7	79.0/12.2	94.2/ 47.7
MVTec	F1max	87.8/18.3	91.4/42.6	91.6 /44.8	93.3 / 47.2	84.6/18.0	88.8/ 47.7
VisA	AUROC	40.4/83.6	47.7/83.9	86.9 /94.2	89.8 / 95.6	58.4/80.5	79.8/ 95.6
VisA	AUPR	11.2/ 84.0	17.0/2.8	61.3 /21.9	69.6 / 25.1	21.5/0.9	53.6/22.2
VisA	F1max	22.1/2.5	25.8/4.2	58.9 /26.4	66.9 / 30.1	28.5/2.0	52.6/ 27.0

TABLE V: Zero-shot cross-domain results on five benchmarks. Values are image-level / pixel-level. Best values are marked in red, second-best values are marked in blue.

Datasets	Shots	Metrics	UniADet (CLIP)	UniADet (DINOv3)	LUMIN (CLIP)	LUMIN (DINOv3)
MVTec	1	AUROC	93.2 /94.8	93.5 / 96.6	91.9/92.0	93.1/ 96.2
		AUPR	96.9 /52.1	97.1 / 56.9	95.8/48.7	96.3/ 57.1
		F1max	92.8/53.0	93.0 / 56.6	94.0 /52.0	92.3/ 55.6
	2	AUROC	93.4/95.2	93.8 / 96.9	95.0 /92.3	93.3/ 96.5
		AUPR	97.1 / 53.5	97.3 / 57.6	97.0/52.0	96.4/ 57.6
		F1max	92.9/54.5	93.4 / 57.4	94.7 /54.3	92.4/ 55.9

TABLE VI: Few-shot results on five benchmarks. Values are image-level/pixel-level. Best values are marked in red, second-best values are marked in blue.

Fig. 4: Segmentation visualization comparison across methods on cable, hazelnut, screw, and transistor. Green: ground truth; red: predictions.

shot	Metrics	Anomaly -CLIP	VisualAD	UniADet (CLIP)	UniADet (DINOv3)	LUMIN (CLIP)	LUMIN (DINOv3)
	model_mem	1.64/1.64	1.59/1.59	1.60/1.60	1.14/1.14	1.60/1.60	1.14/1.14
0	infer_mem	0.39/3.20	1.98/2.00	0.11/0.83	0.14/1.09	0.10/0.78	0.14/1.09
1	infer_mem	—	—	0.16/0.87	0.17/1.12	0.15/0.83	0.17/1.12
2	infer_mem	—	—	0.20/0.92	0.20/1.15	0.19/0.87	0.20/1.15
4	infer_mem	—	—	0.29/1.00	0.26/1.22	0.28/0.96	0.26/1.22
0	time/img	927/894	129/115	93/88	77/74	92/88	75/75

TABLE VII: Inference memory (GB) and per-image time (ms) on MVTec with batch size 1/8 and num_workers 0. Smaller is better.

max_pixel	ratio	time	I-AUROC	P-AUROC	P-AUPR	P-F1max
50,000	0.23%	1.0	98.65	97.75	76.33	69.31
100,000	0.46%	1.0	98.65	97.78	76.61	69.49
200,000	0.92%	1.1	98.65	97.71	75.69	68.70
2,000,000	9.19%	2.3	98.65	97.71	75.71	68.66
21,800,000	100%	20.1	98.65	97.70	75.71	68.66

TABLE VIII: Stratified pixel sampling: effect of sampling ratio on computation time and evaluation metrics.

Fig. 5: Sampling algorithm comparison on speed vs. accuracy. Prefix “S” denotes streaming methods; suffixes “FF” (full feature map) and “MF” (mean-pooled to 1D vector) indicate feature representations. Note that sum_time = 175.4 s (meta) + 26.79 s (mem_build) = 202.1 s. Meta is extracted only once for all experiments.

work_size	meta_time	mem_build_time	total_time	P-AUPR
512	175.2	24.1	199.3	57.99
256	126.7	23.9	150.6	57.95
128	120.4	24.6	145.0	57.91
64	114.5	23.5	138.0	58.09
32	113.3	23.5	136.8	57.99
16	113.1	23.9	137.0	58.04

TABLE IX: PSP hyperparameter ablation: effect of work_size (metadata extraction resolution) on time (s) and P-AUPR.

ratio	meta_time	feat_extract _time	filter_time	mem_build _time	total_time	P-AUPR
1.0	114.6	0	0	3.12	117.7	58.24
2.0	114.6	7.63	2.43	13.31	127.9	58.01
3.0	114.3	11.35	2.06	16.71	131.2	58.02
5.0	114.5	18.26	2.19	23.50	138.0	58.09
8.0	115.6	30.00	2.32	35.70	151.3	58.15
10.0	114.6	37.32	2.23	42.91	157.5	58.05

TABLE X: PSP hyperparameter ablation: effect of coarse_keep_ratio on time (s) and P-AUPR.

Category	5-plugin	2-plugin	$\Delta$
bottle	77.67	77.75	+0.08
cable	27.21	27.05	-0.16
capsule	51.23	51.23	+0.00
carpet	80.68	80.71	+0.03
grid	56.22	56.25	+0.03
hazelnut	64.64	64.41	-0.23

TABLE XI: Plugin ablation: P-AUPR comparison between 5-plugin and 2-plugin (Color+Texture) configurations at

k=20

\Delta

denotes the P-AUPR difference of 2-plugin minus 5-plugin.

Category	ratio=1	ratio=5	ratio=10	max-min
bottle	77.66	77.67	77.67	0.01
cable	27.07	27.21	27.25	0.18
capsule	51.07	51.23	51.40	0.33
carpet	80.64	80.68	80.61	0.07
grid	56.17	56.22	56.32	0.15
hazelnut	64.22	64.64	64.25	0.42

TABLE XII: Per-category effect of coarse_keep_ratio on P-AUPR at

k=20

. Column max-min denotes the range of P-AUPR across three ratio settings.

Metric	CLIP 2L	CLIP 4L	CLIP 5L	DINOv3 2L	DINOv3 4L	DINOv3 5L
I-AUROC	53.7 / 85.4	54.4 / 87.0	51.9 / 87.6	81.6 / 86.0	82.2 / 85.0	81.4 / 86.2
I-AUPR	51.3 / 82.6	51.2 / 82.6	49.9 / 82.5	71.1 / 81.1	71.6 / 76.9	70.7 / 77.6
I-F1max	58.5 / 80.3	58.3 / 80.9	57.6 / 80.3	71.0 / 78.2	71.6 / 76.8	71.0 / 77.2
P-AUROC	79.8 / 94.5	79.1 / 94.3	78.4 / 94.7	94.9 / 95.4	94.5 / 95.3	94.9 / 96.0
P-AUPR	4.4 / 31.8	4.2 / 32.0	4.0 / 32.9	34.5 / 35.9	34.8 / 35.5	34.5 / 37.8
P-F1max	8.2 / 36.3	7.6 / 36.8	7.5 / 37.5	38.5 / 39.3	39.0 / 39.1	38.6 / 41.1

TABLE XIII: Mean results over five benchmarks. Values are of LUMIN/UniADet. 2L, 4L and 5L means training and inference with features (from vision backbone layers)

\{12,24\}

\{6,12,18,24\}

and

\{12,15,18,21,24\}

. Best values are marked in red, second-best values are marked in blue.

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Methods	$k$ =0	$k$ =1	$k$ =4	$k$ =10	$k$ =20	mean_aupr / sum_time
RS (seed 0)	48.56/0	56.73/1.10	57.94/3.06	58.48/7.55	58.64/14.96	57.95/26.67
RS (seed 42)	48.56/0	56.60/1.11	57.85/3.05	58.24/7.48	58.48/15.21	57.79/26.85
FPS_FF	48.56/0	56.71/2.1	57.90/745.3	58.23/2300.5	58.34/5112.8	57.80/8160.6
FPS_MF	48.56/0	56.71/2.1	57.86/712.5	58.08/2110.9	58.33/4367.7	57.74/7193.2
SFPS_FF	48.56/0	56.75/246.2	58.02/275.5	58.24/512.1	58.46/1436.7	57.87/2470.5
SFPS_MF	48.56/0	56.75/242.3	57.93/242.0	58.33/246.7	58.57/251.5	57.90/982.5

Appendix

TABLE XIV: Sampling algorithm comparison: P-AUPR / memory bank build time (s) across

k=0,1,4,10,20

. The last column reports the average P-AUPR and total memory bank building time over all shot settings. Note that sum_time = 175.4 s (meta) + 26.79 s (mem_build) = 202.1 s. Meta is extracted only once for all experiments.

Abbreviation	# feature extractions	Filtering computation complexity	Storage overhead	Core description
RS	0	O(N) shuffle	None	No selection logic, lowest cost
FPS_FF	N	O(K $\cdot$ N $\cdot$ H $\cdot$ W $\cdot$ D)	O(N $\cdot$ H $\cdot$ W $\cdot$ D)	High accuracy but poor deployability
FPS_MF	N	O(K $\cdot$ N $\cdot$ D)	O(N $\cdot$ D)	Mean pooling reduces complexity
SFPS_FF	$\sim$ K $\cdot$ N	O(K 2 $\cdot$ N $\cdot$ H $\cdot$ W $\cdot$ D)	O(K $\cdot$ H $\cdot$ W $\cdot$ D)	Streaming avoids storage, sacrifices time
SFPS_MF	$\sim$ K $\cdot$ N	O(K 2 $\cdot$ N $\cdot$ D)	O(K $\cdot$ D)	Streaming with mean pooling
KM_FF	N	O(K $\cdot$ N $\cdot$ I)	O(N $\cdot$ H $\cdot$ W $\cdot$ D)	High-dimensional clustering, high cost

Appendix

TABLE XV: Theoretical complexity and characteristic comparison of sampling algorithms.

Explore similar work

LiZAD: A Lightweight Zero-Shot Anomaly Detection Framework for Industrial Manufacturing
Jul 2, 2026Uzair Khan, Luigi Capogrosso, Muhammad Aqeel +3Edge Inference Industrial Anomaly Detection
University of Verona · Interdisciplinary Transformation University of Austria · ETH Zurich
Industrial Anomaly Detection via Defect-Grounded Reasoning in Visual Latent Space
Sep 24, 2026Jaron Yeh, Yen-Wei Chang, Jiang Liu +1Industrial Anomaly Detection Anomaly Localization
National Taiwan University · AMD GenAI
InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection
Aug 30, 2026Weifei Chen, Honghao Zhang, Zhiyuan You +1Industrial Anomaly Detection Zero-Shot Anomaly Detection
Shanghai Jiao Tong University · The Chinese University of Hong Kong

Jul 2, 2026J/K move · Enter open · S save

LiZAD: A Lightweight Zero-Shot Anomaly Detection Framework for Industrial Manufacturing

Uzair Khan, Luigi Capogrosso, Muhammad Aqeel, Francesco Setti+2

University of Verona · Interdisciplinary Transformation University of Austria · ETH Zurich

Edge Inference Industrial Anomaly Detection Vision Foundation Model Adaptation Anomaly Localization Zero-Shot Anomaly Detection

Open paper AskPDF arXiv

In modern high-throughput industrial production lines, product configurations and visual characteristics frequently change, making it impractical to collect and annotate data for every new scenario. This dynamic setting makes Zero-Shot Anomaly Detection (ZSAD) particularly suitable, as it enables defect detection without requiring training on target-specific samples. Although recent ZSAD approaches show promising results, they are computationally intensive and thus unsuitable for deployment on resource-constrained devices. We propose LiZAD: a lightweight framework designed for real-time ZSAD specifically tailored for use on edge devices. The proposed approach pairs the dense and spatially aware visual features of DINOv3, crucial for precise pixel-level localization, with the highly computationally efficient text embeddings of MobileCLIP2. These features are then mapped into a shared latent space via low-memory trainable projection heads. Compared to six state-of-the-art ZSAD models, LiZAD achieves an average memory reduction of 61.5%, a parameter reduction of 74.6%, and a speedup of 3.02x in terms of latency. Despite substantial reductions in computational and memory costs, our approach maintains competitive anomaly detection performance, dropping the average P-AUROC by just 6.4% relative to the best state-of-the-art model across the VisA, BTAD, MPDD, and MVTec-AD datasets. Finally, it is successfully deployed on the NVIDIA Jetson NX and Jetson AGX edge devices and tested on the real production line of the Industrial Computer Engineering Laboratory (ICE Lab) at the University of Verona. The code is available at https://github.com/intelligolabs/LiZAD.

Abstract

Explore similar work

LiZAD: A Lightweight Zero-Shot Anomaly Detection Framework for Industrial Manufacturing

Industrial Anomaly Detection via Defect-Grounded Reasoning in Visual Latent Space

InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection