# P-ODN: Prototype based Open Deep Network for Open Set Recognition

arXiv: https://arxiv.org/abs/1905.01851 · HTML: https://mlsanity.com/paper/1905.01851/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2019.

## Built on by (most cited first, 28 of 28)

- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Open-Set Recognition: a Good Closed-Set Classifier is All You Need?](https://mlsanity.com/paper/2110.06207/) (2021)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery](https://mlsanity.com/paper/2310.19776/) (2023)
- [SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery](https://mlsanity.com/paper/2408.14371/) (2024)
- [OpenTAL: Towards Open Set Temporal Action Localization](https://mlsanity.com/paper/2203.05114/) (2022)
- [Entropic Open-set Active Learning](https://mlsanity.com/paper/2312.14126/) (2023)
- [Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2206.07551/) (2022)
- [Attribute Prototype Network for Any-Shot Learning](https://mlsanity.com/paper/2204.01208/) (2022)
- [3DOS: Towards 3D Open Set Learning -- Benchmarking and Understanding Semantic Novelty Detection on Point Clouds](https://mlsanity.com/paper/2207.11554/) (2022)
- [LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition](https://mlsanity.com/paper/2309.12780/) (2023)
- [SMART-Vision: Survey of Modern Action Recognition Techniques in Vision](https://mlsanity.com/paper/2501.13066/) (2025)
- [Continual Learning for Autonomous Robots: A Prototype-based Approach](https://mlsanity.com/paper/2404.00418/) (2024)
- [Video Action Recognition Collaborative Learning with Dynamics via PSO-ConvNet Transformer](https://mlsanity.com/paper/2302.09187/) (2023)
- [ProtoDiffusion: Classifier-Free Diffusion Guidance with Prototype Learning](https://mlsanity.com/paper/2307.01924/) (2023)
- [OneRing: A Simple Method for Source-free Open-partial Domain Adaptation](https://mlsanity.com/paper/2206.03600/) (2022)
- [Learning Large Margin Sparse Embeddings for Open Set Medical Diagnosis](https://mlsanity.com/paper/2307.04541/) (2023)
- [Multi-Attribute Open Set Recognition](https://mlsanity.com/paper/2208.06809/) (2022)
- [Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2509.01275/) (2025)
- [Prototype Fission: Closing Set for Robust Open-set Semi-supervised Learning](https://mlsanity.com/paper/2308.15575/) (2023)
- [Proxy-Anchor and EVT-Driven Continual Learning Method for Generalized Category Discovery](https://mlsanity.com/paper/2504.08550/) (2025)
- [Open-Set Representation Learning through Combinatorial Embedding](https://mlsanity.com/paper/2106.15278/) (2021)
- [Supervised Contrastive Prototype Learning: Augmentation Free Robust Neural Network](https://mlsanity.com/paper/2211.14424/) (2022)
- [GROOD: GRadient-Aware Out-of-Distribution Detection](https://mlsanity.com/paper/2312.14427/) (2023)
- [Cascading Unknown Detection with Known Classification for Open Set Recognition](https://mlsanity.com/paper/2406.06351/) (2024)
- [Database-Agnostic Gait Enrollment using SetTransformers](https://mlsanity.com/paper/2505.02815/) (2025)
- [Few-shot Unknown Class Discovery of Hyperspectral Images with Prototype Learning and Clustering](https://mlsanity.com/paper/2508.18075/) (2025)
- [A Novel Latent-Class Attack and its Detection by Class Subspace Orthogonalization](https://mlsanity.com/paper/2606.29112/) (2026)

## Abstract (arXiv)

Most of the existing recognition algorithms are proposed for closed set scenarios, where all categories are known beforehand. However, in practice, recognition is essentially an open set problem. There are categories we know called "knowns", and there are more we do not know called "unknowns". Enumerating all categories beforehand is never possible, consequently it is infeasible to prepare sufficient training samples for those unknowns. Applying closed set recognition methods will naturally lead to unseen-category errors. To address this problem, we propose the prototype based Open Deep Network (P-ODN) for open set recognition tasks. Specifically, we introduce prototype learning into open set recognition. Prototypes and prototype radiuses are trained jointly to guide a CNN network to derive more discriminative features. Then P-ODN detects the unknowns by applying a multi-class triplet thresholding method based on the distance metric between features and prototypes. Manual labeling the unknowns which are detected in the previous process as new categories. Predictors for new categories are added to the classification layer to "open" the deep neural networks to incorporate new categories dynamically. The weights of new predictors are initialized exquisitely by applying a distances based algorithm to transfer the learned knowledge. Consequently, this initialization method speed up the fine-tuning process and reduce the samples needed to train new predictors. Extensive experiments show that P-ODN can effectively detect unknowns and needs only few samples with human intervention to recognize a new category. In the real world scenarios, our method achieves state-of-the-art performance on the UCF11, UCF50, UCF101 and HMDB51 datasets.