mlsanityData to 7 Oct 2026

Adversarial Motorial Prototype Framework for Open Set Recognition

arXiv 2108.04225 ↗First posted 13 Jul 2021cs.CV cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Open set recognition is designed to identify known classes and to reject unknown classes simultaneously. Specifically, identifying known classes and rejecting unknown classes correspond to reducing the empirical risk and the open space risk, respectively. First, the motorial prototype framework (MPF) is proposed, which classifies known classes according to the prototype classification idea. Moreover, a motorial margin constraint term is added into the loss function of the MPF, which can further improve the clustering compactness of known classes in the feature space to reduce both risks. Second, this paper proposes the adversarial motorial prototype framework (AMPF) based on the MPF. On the one hand, this model can generate adversarial samples and add these samples into the training phase; on the other hand, it can further improve the differential mapping ability of the model to known and unknown classes with the adversarial motion of the margin constraint radius. Finally, this paper proposes an upgraded version of the AMPF, AMPF++, which adds much more generated unknown samples into the training phase. In this paper, a large number of experiments prove that the performance of the proposed models is superior to that of other current works.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 24 of its 56 references that are in the map. First posted on arXiv 13 Jul 2021.

Builds on

24 of 56 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2019Natural Adversarial Examplescited by 1,401
  5. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  6. 2015Towards Open Set Deep Networkscited by 533
  7. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  8. 2018Recent Advances in Open Set Recognition: A Surveycited by 309
  9. 2018Reducing Network Agnostophobiacited by 165
  10. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  11. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  12. 2018Classification-Reconstruction Learning for Open-Set Recognitioncited by 146
12 more
  1. 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
  2. 2018Robust Classification with Convolutional Prototype Learningcited by 122
  3. 2021Learning Placeholders for Open-Set Recognitioncited by 121
  4. 2020Learning Open Set Network with Discriminative Reciprocal Pointscited by 115
  5. 2020Hybrid Models for Open Set Recognitioncited by 109
  6. 2020Conditional Gaussian Distribution Learning for Open Set Recognitioncited by 104
  7. 2018Learning a Neural-network-based Representation for Open Set Recognitioncited by 40
  8. 2017Open-Category Classification by Adversarial Sample Generationcited by 24
  9. 2018Unseen Class Discovery in Open-world Classificationcited by 20
  10. 2021Conditional Variational Capsule Network for Open Set Recognitioncited by 17
  11. 2019Deep CNN-based Multi-task Learning for Open-Set Recognitioncited by 12
  12. 2017Adversarial Robustness: Softmax versus Openmaxcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 1.

4 papers.

  1. 2022Open Set Recognition using Vision Transformer with an Additional Detection Headcited by 2
  2. 2023Latent Space Energy-based Model for Fine-grained Open Set Recognitioncited by 2
  3. 2024Taking Class Imbalance Into Account in Open Set Recognition Evaluationcited by 1
  4. 2023Open-World Object Detection via Discriminative Class Prototype Learningcited by 0