mlsanityData to 7 Oct 2026

Taking Class Imbalance Into Account in Open Set Recognition Evaluation

arXiv 2402.06331 ↗First posted 9 Feb 2024cs.LG cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

In recent years Deep Neural Network-based systems are not only increasing in popularity but also receive growing user trust. However, due to the closed-world assumption of such systems, they cannot recognize samples from unknown classes and often induce an incorrect label with high confidence. Presented work looks at the evaluation of methods for Open Set Recognition, focusing on the impact of class imbalance, especially in the dichotomy between known and unknown samples. As an outcome of problem analysis, we present a set of guidelines for evaluation of methods in this field.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 55 references that are in the map. First posted on arXiv 9 Feb 2024.

Builds on

18 of 55 references.

References · 18

  1. 2015Towards Open Set Deep Networkscited by 533
  2. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 446
  3. 2018Recent Advances in Open Set Recognition: A Surveycited by 309
  4. 2017Data Augmentation Generative Adversarial Networkscited by 278
  5. 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 259
  6. 2014Towards Open World Recognitioncited by 226
  7. 2020A Review of Generalized Zero-Shot Learning Methodscited by 159
  8. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  9. 2018Classification-Reconstruction Learning for Open-Set Recognitioncited by 146
  10. 2020Learning Open Set Network with Discriminative Reciprocal Pointscited by 115
  11. 2017DOC: Deep Open Classification of Text Documentscited by 109
  12. 2021Understanding Softmax Confidence and Uncertaintycited by 62
6 more
  1. 2020Interpretability and Explainability: A Machine Learning Zoo Mini-tourcited by 55
  2. 2017Open-Category Classification by Adversarial Sample Generationcited by 24
  3. 2020Open Set Recognition with Conditional Probabilistic Generative Modelscited by 10
  4. 2020Imbalanced classification: a paradigm-based reviewcited by 5
  5. 2021Adversarial Motorial Prototype Framework for Open Set Recognitioncited by 4
  6. 2023torchosr -- a PyTorch extension package for Open Set Recognition models evaluation in Pythoncited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Synthetic Non-stationary Data Streams for Recognition of the Unknowncited by 4