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

• URL: http://arxiv.org/abs/2604.23729v1
• Date: Sun, 26 Apr 2026 14:15:35 GMT
• Title: DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detection
• Abstract summary: DynProto is a novel approach that learns OOD prototypes dynamically during testing using only in-distribution (ID) information.<n>We leverage easy-to-detect OOD samples as anchors'' to find their harder-to-detect, similar counterparts.<n>DynProto significantly outperforms prior methods across multiple benchmarks.
• Score: 42.39636668725844
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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: \textbf{Coarse OOD Pattern Capturing Module} caches OOD patterns that are easily confused with each ID class during testing, and \textbf{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.

Related papers

• Prototype Fusion: A Training-Free Multi-Layer Approach to OOD Detection [0.8394724589095839]
  We show that intermediate layers encode equally rich and discriminative information for OOD detection.<n>We propose a model-agnostic approach that leverages internal representations across multiple layers.<n>Our approach delivers robust, architecture-agnostic performance and strong generalization for image classification.
  arXiv  Detail & Related papers  (2026-03-24T19:32:13Z)
• DCAC: Dynamic Class-Aware Cache Creates Stronger Out-of-Distribution Detectors [43.8920190045364]
  Out-of-distribution (OOD) detection remains a fundamental challenge for deep neural networks.<n>We propose DCAC (Dynamic Class-Aware Cache), a training-free, test-time calibration module that maintains separate caches for each ID class to collect high-entropy samples.
  arXiv  Detail & Related papers  (2026-01-18T16:16:31Z)
• Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity [15.305171289133463]
  Neural networks that are trained on limited category samples often mispredict out-of-distribution (OOD) objects.<n>We observe that features of the same category are more tightly clustered in feature space, while those of different categories are more dispersed.<n>We introduce a novel OOD detection network structure (Proto-OOD)<n>Proto-OOD enhances the representativeness of category prototypes using contrastive loss and detects OOD data by evaluating the similarity between input features and category prototypes.
  arXiv  Detail & Related papers  (2024-09-09T09:48:27Z)
• Can OOD Object Detectors Learn from Foundation Models? [56.03404530594071]
  Out-of-distribution (OOD) object detection is a challenging task due to the absence of open-set OOD data. Inspired by recent advancements in text-to-image generative models, we study the potential of generative models trained on large-scale open-set data to synthesize OOD samples. We introduce SyncOOD, a simple data curation method that capitalizes on the capabilities of large foundation models.
  arXiv  Detail & Related papers  (2024-09-08T17:28:22Z)
• Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox [70.57120710151105]
  Most existing out-of-distribution (OOD) detection benchmarks classify samples with novel labels as the OOD data. Some marginal OOD samples actually have close semantic contents to the in-distribution (ID) sample, which makes determining the OOD sample a Sorites Paradox. We construct a benchmark named Incremental Shift OOD (IS-OOD) to address the issue.
  arXiv  Detail & Related papers  (2024-06-14T09:27:56Z)
• Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Models [71.39421638547164]
  We propose to detect OOD molecules by adopting an auxiliary diffusion model-based framework, which compares similarities between input molecules and reconstructed graphs. Due to the generative bias towards reconstructing ID training samples, the similarity scores of OOD molecules will be much lower to facilitate detection. Our research pioneers an approach of Prototypical Graph Reconstruction for Molecular OOD Detection, dubbed as PGR-MOOD and hinges on three innovations.
  arXiv  Detail & Related papers  (2024-04-24T03:25:53Z)
• GROOD: GRadient-Aware Out-of-Distribution Detection [11.511906612904255]
  Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models in real-world applications.<n>We propose GRadient-aware Out-Of-Distribution detection (GROOD), a method that derives an OOD prototype from synthetic samples and computes class prototypes directly from In-distribution (ID) training data.
  arXiv  Detail & Related papers  (2023-12-22T04:28:43Z)
• General-Purpose Multi-Modal OOD Detection Framework [5.287829685181842]
  Out-of-distribution (OOD) detection identifies test samples that differ from the training data, which is critical to ensuring the safety and reliability of machine learning (ML) systems. We propose a general-purpose weakly-supervised OOD detection framework, called WOOD, that combines a binary classifier and a contrastive learning component. We evaluate the proposed WOOD model on multiple real-world datasets, and the experimental results demonstrate that the WOOD model outperforms the state-of-the-art methods for multi-modal OOD detection.
  arXiv  Detail & Related papers  (2023-07-24T18:50:49Z)
• AUTO: Adaptive Outlier Optimization for Test-Time OOD Detection [79.51071170042972]
  Out-of-distribution (OOD) detection aims to detect test samples that do not fall into any training in-distribution (ID) classes.<n>Data safety and privacy make it infeasible to collect task-specific outliers in advance for different scenarios.<n>We present test-time OOD detection, which allows the deployed model to utilize real OOD data from the unlabeled data stream during testing.
  arXiv  Detail & Related papers  (2023-03-22T02:28:54Z)
• Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need [52.88953913542445]
  We find surprisingly that simply using reconstruction-based methods could boost the performance of OOD detection significantly. We take Masked Image Modeling as a pretext task for our OOD detection framework (MOOD)
  arXiv  Detail & Related papers  (2023-02-06T08:24:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.