Prototype Fusion: A Training-Free Multi-Layer Approach to OOD Detection

Shreen Gul; Mohamed Elmahallawy; Ardhendu Tripathy; Sanjay Madria

cs.CVMar 24, 2026

Prototype Fusion: A Training-Free Multi-Layer Approach to OOD Detection

Authors: Shreen Gul, Mohamed Elmahallawy, Ardhendu Tripathy, Sanjay Madria

Organizations: Missouri University of Science and Technology, Rolla, MO 65401, USA · Washington State University, Richland, WA 99354, USA

Abstract

Deep learning models are increasingly deployed in safety-critical applications, where reliable out-of-distribution (OOD) detection is essential to ensure robustness. Existing methods predominantly rely on the penultimate-layer activations of neural networks, assuming they encapsulate the most informative in-distribution (ID) representations. In this work, we revisit this assumption to show that intermediate layers encode equally rich and discriminative information for OOD detection. Based on this observation, we propose a simple yet effective model-agnostic approach that leverages internal representations across multiple layers. Our scheme aggregates features from successive convolutional blocks, computes class-wise mean embeddings, and applies L_2 normalization to form compact ID prototypes capturing class semantics. During inference, cosine similarity between test features and these prototypes serves as an OOD score--ID samples exhibit strong affinity to at least one prototype, whereas OOD samples remain uniformly distant. Extensive experiments on state-of-the-art OOD benchmarks across diverse architectures demonstrate that our approach delivers robust, architecture-agnostic performance and strong generalization for image classification. Notably, it improves AUROC by up to 4.41% and reduces FPR by 13.58%, highlighting multi-layer feature aggregation as a powerful yet underexplored signal for OOD detection, challenging the dominance of penultimate-layer-based methods. Our code is available at: https://github.com/sgchr273/cosine-layers.git.

Figures & tables

Figure 1: Overview of the proposed training-free OOD detector. A pretrained CNN is tapped at layers $\ell_{1}$ – $\ell_{3}$ . ID calibration images are passed through the network, and per-layer features are global-average-pooled and $L_{2}$ -normalized to form $K$ class prototypes (green regions). For a test image (ID or OOD), we compute cosine similarity between its features and each layer’s prototypes (green arrows for ID, red arrows for OOD). At each layer, we retain the maximum class-wise similarity, and these per-layer maxima are averaged to produce an ID affinity score, with $\text{OODScore}=1-\text{affinity}$ . The heatmaps on the right show that ID samples yield strong, consistent similarities across layers and classes, whereas OOD samples produce weaker and less coherent similarity patterns.

Model	Method	iSUN		LSUN		Places		iNat		Textures		Average
Model	Method	AUROC $\uparrow$	FPR $\downarrow$	AUROC $\uparrow$	FPR $\downarrow$	AUROC $\uparrow$	FPR $\downarrow$	AUROC $\uparrow$	FPR $\downarrow$	AUROC $\uparrow$	FPR $\downarrow$	AUROC $\uparrow$	FPR $\downarrow$
ResNet-18	MSP	89.79	47.44	94.68	15.26	89.66	48.32	89.59	44.33	87.18	63.96	90.75	39.75
	MaxLogit	90.08	52.84	94.63	25.82	89.65	55.06	89.37	51.19	86.35	73.86	90.74	46.60
	Energy	88.42	63.00	92.34	51.48	87.97	62.87	87.46	59.14	84.24	79.10	89.02	57.46
	Mahalanobis	86.86	51.32	80.99	53.84	84.80	49.93	80.25	58.48	92.64	34.99	86.61	46.26
	GradNorm	83.44	70.92	91.86	37.20	79.30	74.98	90.81	44.29	81.20	82.75	86.56	57.97

Table 1: OOD detection results on the CIFAR-10 dataset.

\uparrow

\downarrow

denote that higher/lower values are better. The first , second , and third best results are highlighted in green, orange, and blue, respectively (values in %).

Panel of Figure 2 — Figure 2: Effect of calibration set size on AUROC (top row) and false positive rate (bottom row) for CIFAR-10, CIFAR-100, and ImageNet-1k.

		ID = CIFAR-10						ID = CIFAR-100
Model	Method	CIFAR-100		SVHN		Average		CIFAR-10		SVHN		Average
		AUROC $\uparrow$	FPR $\downarrow$	AUROC $\uparrow$	FPR $\downarrow$	AUROC $\uparrow$	FPR $\downarrow$	AUROC $\uparrow$	FPR $\downarrow$	AUROC $\uparrow$	FPR $\downarrow$	AUROC $\uparrow$	FPR $\downarrow$
ResNet-18	MSP	88.76	46.29	93.60	19.17	91.18	32.73	75.62	77.26	72.92	83.01	74.27	80.14
	MaxLogit	88.09	53.99	94.36	20.86	91.22	37.42	72.75	84.39	67.27	90.25	70.01	87.32
	Energy	85.04	64.90	93.69	29.20	89.37	47.05	66.38	86.81	58.26	91.68	62.32	89.25
	Mahalanobis	82.11	59.59	94.12	29.00	88.12	44.30	70.44	78.46	77.92	61.76	74.18	70.11

Table 2: OOD detection results where CIFAR-10 is ID and OOD = CIFAR-100, SVHN) and ID = CIFAR-100 (OOD = CIFAR-10, SVHN).

\uparrow

\downarrow

denote that higher/lower is better. The first , second , and third best results are highlighted in green, orange, and blue respectively (values in %).

Model	Method	SUN		Places		iNat		Textures		Average
Model	Method	AUROC $\uparrow$	FPR $\downarrow$	AUROC $\uparrow$	FPR $\downarrow$	AUROC $\uparrow$	FPR $\downarrow$	AUROC $\uparrow$	FPR $\downarrow$	AUROC $\uparrow$	FPR $\downarrow$
ResNet-50	MSP	79.25	79.48	77.48	78.59	84.65	62.69	74.78	87.76	79.04	77.13
	MaxLogit	74.78	85.81	72.64	85.90	80.25	76.47	69.25	91.74	74.23	84.98
	Energy	50.82	89.72	50.55	90.23	51.27	87.51	48.57	94.28	50.30	90.44
	Mahalanobis	79.60	54.97	77.26	65.66	90.48	29.89	87.13	53.09	83.62	50.90
	GradNorm	30.01	94.09	29.56	95.31	30.72	90.89	39.25	91.06	32.38	92.84

Table 3: OOD detection results on the ImageNet-1k dataset.

\uparrow

\downarrow

denote that higher/lower values are better. The first , second , and third best results are highlighted in green, orange, and blue, respectively (values in %).

Figure 3: AUROC and FPR using the penultimate layer vs. the last three layers across three ID datasets: CIFAR-10 (Exp1), CIFAR-100 (Exp2), and ImageNet-1K (Exp3).

Figure 4: Impact of weighting schemes across layers on overall detection performance.

Figure 5: Per-layer cosine similarity scores for the last three layers of ResNet-18 on ID data (CIFAR-10)and four OOD datasets (SVHN, Textures, LSUN, Places).

OOD Detection

Out-of-distribution (OOD) detection identifies inputs unlike a model’s training data so systems can flag uncertainty, reject inputs, or adapt safely.

See all 215 papers

DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detection
Apr 26, 2026Yanqi Wu, Xinhua Lu, Runhe Lai +4Prototype-Based Classification OOD Detection
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510275, China · Peng Cheng Laboratory, Shenzhen 518066, China · Key Laboratory of Machine Intelligence and Advanced Computing, MOE, Guangzhou 510275, China +2
MM++: Post-Hoc Scale-Invariant Multilayer OOD Detection via Top-K Gated Feature Fusion
Jun 15, 2026Rahim Hossain, Md Tawheedul Islam Bhuian, Md Farhan Shadiq +1Diffusion-Based OOD Detection OOD Detection
School of Computing State University of New York at Binghamton
Unified Multi-Layer Subspace Modeling for Cross-Domain OOD Detection
Sep 6, 2026Gerhard Krumpl, Henning Avenhaus, Horst PosseggerOOD Detection
Institute of Visual Computing, Graz University of Technology, Austria · KESTRELEYE GmbH, Austria

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

DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detection

Yanqi Wu, Xinhua Lu, Runhe Lai, Qichao Chen+3

School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510275, China · Peng Cheng Laboratory, Shenzhen 518066, China · Key Laboratory of Machine Intelligence and Advanced Computing, MOE, Guangzhou 510275, China+2

Prototype-Based Classification OOD Detection

Open paper AskPDF arXiv

Recent studies show that using potential out-of-distribution (OOD) labels from large corpora as auxiliary information can improve OOD detection in vision-language models (VLMs). However, these methods often fail when real-world OOD samples fall outside the predefined OOD label set. To address this limitation, we propose DynProto, a novel approach that learns OOD prototypes dynamically during testing using only in-distribution (ID) information. DynProto is inspired by a key observation: OOD samples predicted as the same ID class tend to cluster in the feature space. With this insight, we leverage easy-to-detect OOD samples as ``anchors'' to find their harder-to-detect, similar counterparts. To this end, DynProto introduces two modules: Coarse OOD Pattern Capturing Module caches OOD patterns that are easily confused with each ID class during testing, and Fine-grained OOD Pattern Refinement Module subsequently clusters these patterns within each cache and aggregates them into representative OOD prototypes. By measuring similarity to ID and dynamic OOD prototypes, DynProto enables accurate OOD detection. DynProto significantly outperforms prior methods across multiple benchmarks. On ImageNet OOD benchmark, DynProto reduces FPR95 by 11.60% and improves AUROC by 4.70%. Moreover, the framework is architecture-agnostic and can be integrated into various backbones.

Abstract

OOD Detection

Explore similar work

DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detection

MM++: Post-Hoc Scale-Invariant Multilayer OOD Detection via Top-K Gated Feature Fusion

Unified Multi-Layer Subspace Modeling for Cross-Domain OOD Detection