mlsanityData to 14 Oct 2026

Recognition Awareness: An Application of Latent Cognizance to Open-Set Recognition

arXiv 2108.12115 ↗First posted 27 Aug 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This study investigates an application of a new probabilistic interpretation of a softmax output to Open-Set Recognition (OSR). Softmax is a mechanism wildly used in classification and object recognition. However, a softmax mechanism forces a model to operate under a closed-set paradigm, i.e., to predict an object class out of a set of pre-defined labels. This characteristic contributes to efficacy in classification, but poses a risk of non-sense prediction in object recognition. Object recognition is often operated under a dynamic and diverse condition. A foreign object -- an object of any unprepared class -- can be encountered at any time. OSR is intended to address an issue of identifying a foreign object in object recognition. Based on Bayes theorem and the emphasis of conditioning on the context, softmax inference has been re-interpreted. This re-interpretation has led to a new approach to OSR, called Latent Cognizance (LC). Our investigation employs various scenarios, using Imagenet 2012 dataset as well as fooling and open-set images. The findings support LC hypothesis and show its effectiveness on OSR.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 31 references that are in the map. First posted on arXiv 27 Aug 2021.

Builds on

15 of 31 references.

References · 15

  1. 2013Intriguing properties of neural networkscited by 5,155
  2. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2016Improved Techniques for Training GANscited by 2,970
  5. 2017Improved Training of Wasserstein GANscited by 2,235
  6. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  7. 2015Towards Open Set Deep Networkscited by 538
  8. 2018Recent Advances in Open Set Recognition: A Surveycited by 310
  9. 2014Caffe: Convolutional Architecture for Fast Feature Embeddingcited by 288
  10. 2017Breaking the Softmax Bottleneck: A High-Rank RNN Language Modelcited by 152
  11. 2018Classification-Reconstruction Learning for Open-Set Recognitioncited by 146
  12. 2017BEGAN: Boundary Equilibrium Generative Adversarial Networkscited by 121
3 more
  1. 2015The Extreme Value Machinecited by 78
  2. 2018Classification Uncertainty of Deep Neural Networks Based on Gradient Informationcited by 43
  3. 2018Sigsoftmax: Reanalysis of the Softmax Bottleneckcited by 20

Built on by

Not cited yet.