Finding the Unknown: Novelty Detection with Extreme Value Signatures of Deep Neural Activations
| Autor: | Alexander Schultheiss, Christoph Käding, Joachim Denzler, Alexander Freytag |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
business.industry
Computer science Small number Pattern recognition 02 engineering and technology 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Novelty detection Convolutional neural network Visual recognition Discriminative model 0202 electrical engineering electronic engineering information engineering Leverage (statistics) 020201 artificial intelligence & image processing Artificial intelligence business Extreme value theory computer 0105 earth and related environmental sciences Intuition |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783319667089 GCPR |
| DOI: | 10.1007/978-3-319-66709-6_19 |
| Popis: | Achieving or even surpassing human-level accuracy became recently possible in a variety of application scenarios due to the rise of convolutional neural networks (CNNs) trained from large datasets. However, solving supervised visual recognition tasks by discriminating among known categories is only one side of the coin. In contrast to this, novelty detection is still an unsolved task where instances of yet unknown categories need to be identified. Therefore, we propose to leverage the powerful discriminative nature of CNNs to novelty detection tasks by investigating class-specific activation patterns. More precisely, we assume that a semantic category can be described by its extreme value signature, that specifies which dimensions of deep neural activations have largest values. By following this intuition, we show that already a small number of high-valued dimensions allows to separate known from unknown categories. Our approach is simple, intuitive, and can be easily put on top of CNNs trained for vanilla classification tasks. We empirically validate the benefits of our approach in terms of accuracy and speed by comparing it against established methods in a variety of novelty detection tasks derived from ImageNet. Finally, we show that visualizing extreme value signatures allows to inspect class-specific patterns learned during training which may ultimately help to better understand CNN models. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|