# Classification-Reconstruction Learning for Open-Set Recognition

arXiv: https://arxiv.org/abs/1812.04246 · HTML: https://mlsanity.com/paper/1812.04246/

## Key facts

- Cited by 146 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2018.

## Built on by (most cited first, 30 of 146)

- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [SSD: A Unified Framework for Self-Supervised Outlier Detection](https://mlsanity.com/paper/2103.12051/) (2021)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges](https://mlsanity.com/paper/2110.14051/) (2021)
- [Counterfactual Zero-Shot and Open-Set Visual Recognition](https://mlsanity.com/paper/2103.00887/) (2021)
- [OVANet: One-vs-All Network for Universal Domain Adaptation](https://mlsanity.com/paper/2104.03344/) (2021)
- [Class-Aware Contrastive Semi-Supervised Learning](https://mlsanity.com/paper/2203.02261/) (2022)
- [Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection](https://mlsanity.com/paper/2203.02194/) (2022)
- [Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2104.06601/) (2021)
- [UC-OWOD: Unknown-Classified Open World Object Detection](https://mlsanity.com/paper/2207.11455/) (2022)
- [Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery](https://mlsanity.com/paper/2310.19776/) (2023)
- [Learning to Detect Every Thing in an Open World](https://mlsanity.com/paper/2112.01698/) (2021)
- [Open-world Machine Learning: Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2105.13448/) (2021)
- [SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery](https://mlsanity.com/paper/2408.14371/) (2024)
- [OpenAUC: Towards AUC-Oriented Open-Set Recognition](https://mlsanity.com/paper/2210.13458/) (2022)
- [Progressive Open Space Expansion for Open-Set Model Attribution](https://mlsanity.com/paper/2303.06877/) (2023)
- [Class-Specific Semantic Reconstruction for Open Set Recognition](https://mlsanity.com/paper/2207.02158/) (2022)
- [Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approaches](https://mlsanity.com/paper/2102.05897/) (2021)
- [Learning Bounds for Open-Set Learning](https://mlsanity.com/paper/2106.15792/) (2021)
- [PMAL: Open Set Recognition via Robust Prototype Mining](https://mlsanity.com/paper/2203.08569/) (2022)
- [Uncertainty for Identifying Open-Set Errors in Visual Object Detection](https://mlsanity.com/paper/2104.01328/) (2021)
- [A Survey on Open Set Recognition](https://mlsanity.com/paper/2109.00893/) (2021)
- [Few-Shot Continual Active Learning by a Robot](https://mlsanity.com/paper/2210.04137/) (2022)
- [Difficulty-Aware Simulator for Open Set Recognition](https://mlsanity.com/paper/2207.10024/) (2022)
- [Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization](https://mlsanity.com/paper/2308.09391/) (2023)
- [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)
- [Open-set Adversarial Defense with Clean-Adversarial Mutual Learning](https://mlsanity.com/paper/2202.05953/) (2022)
- [Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach](https://mlsanity.com/paper/2110.04514/) (2021)
- [Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalization](https://mlsanity.com/paper/2404.00710/) (2024)

## Abstract (arXiv)

Open-set classification is a problem of handling `unknown' classes that are not contained in the training dataset, whereas traditional classifiers assume that only known classes appear in the test environment. Existing open-set classifiers rely on deep networks trained in a supervised manner on known classes in the training set; this causes specialization of learned representations to known classes and makes it hard to distinguish unknowns from knowns. In contrast, we train networks for joint classification and reconstruction of input data. This enhances the learned representation so as to preserve information useful for separating unknowns from knowns, as well as to discriminate classes of knowns. Our novel Classification-Reconstruction learning for Open-Set Recognition (CROSR) utilizes latent representations for reconstruction and enables robust unknown detection without harming the known-class classification accuracy. Extensive experiments reveal that the proposed method outperforms existing deep open-set classifiers in multiple standard datasets and is robust to diverse outliers. The code is available in https://nae-lab.org/~rei/research/crosr/.