mlsanityData to 7 Oct 2026

A novel network training approach for open set image recognition

arXiv 2109.12756 ↗First posted 27 Sep 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Convolutional Neural Networks (CNNs) are commonly designed for closed set arrangements, where test instances only belong to some "Known Known" (KK) classes used in training. As such, they predict a class label for a test sample based on the distribution of the KK classes. However, when used under the Open Set Recognition (OSR) setup (where an input may belong to an "Unknown Unknown" or UU class), such a network will always classify a test instance as one of the KK classes even if it is from a UU class. As a solution, recently, data augmentation based on Generative Adversarial Networks(GAN) has been used. In this work, we propose a novel approach for mining a "Known UnknownTrainer" or KUT set and design a deep OSR Network (OSRNet) to harness this dataset. The goal isto teach OSRNet the essence of the UUs through KUT set, which is effectively a collection of mined "hard Known Unknown negatives". Once trained, OSRNet can detect the UUs while maintaining high classification accuracy on KKs. We evaluate OSRNet on six benchmark datasets and demonstrate it outperforms contemporary OSR methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 48 references that are in the map. First posted on arXiv 27 Sep 2021.

Builds on

27 of 48 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  5. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  6. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  7. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  8. 2015Towards Open Set Deep Networkscited by 533
  9. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  10. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  11. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  12. 2017MMD GAN: Towards Deeper Understanding of Moment Matching Networkcited by 251
15 more
  1. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  2. 2018Pros and Cons of GAN Evaluation Measurescited by 224
  3. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  4. 2018Reducing Network Agnostophobiacited by 165
  5. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  6. 2018Classification-Reconstruction Learning for Open-Set Recognitioncited by 146
  7. 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
  8. 2018Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifierscited by 126
  9. 2015The Extreme Value Machinecited by 78
  10. 2016Adversarial Examples Detection in Deep Networks with Convolutional Filter Statisticscited by 77
  11. 2016A Boundary Tilting Persepective on the Phenomenon of Adversarial Examplescited by 70
  12. 2019Out-of-Distribution Detection for Generalized Zero-Shot Action Recognitioncited by 54
  13. 2017Sparse Representation-based Open Set Recognitioncited by 36
  14. 2018Distortion Robust Image Classification using Deep Convolutional Neural Network with Discrete Cosine Transformcited by 10
  15. 2018High Dimensional Spaces, Deep Learning and Adversarial Examplescited by 5

Built on by

Not cited yet.