Detecting unseen targets during inference in infrared imaging
| Autor: | Antoine d'Acremont, Guillaume Quin, Alexandre Baussard, Thibault Le Du, Ronan Fablet |
|---|---|
| Přispěvatelé: | Lab-STICC_ENSTAB_CID_TOMS, Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC), Institut Mines-Télécom [Paris] (IMT)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-École Nationale d'Ingénieurs de Brest (ENIB)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Centre National de la Recherche Scientifique (CNRS)-Université Bretagne Loire (UBL)-Institut Mines-Télécom [Paris] (IMT)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-École Nationale d'Ingénieurs de Brest (ENIB)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Centre National de la Recherche Scientifique (CNRS)-Université Bretagne Loire (UBL), MBDA France (MBDA), MBDA France, Lab-STICC_IMTA_CID_TOMS, Département Signal et Communications (IMT Atlantique - SC), IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT) |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Local outlier factor
Computer science business.industry Deep learning Inference 02 engineering and technology Machine learning computer.software_genre Convolutional neural network Novelty detection 030218 nuclear medicine & medical imaging Support vector machine 03 medical and health sciences 0302 clinical medicine Robustness (computer science) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Anomaly detection Artificial intelligence business computer [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing ComputingMilieux_MISCELLANEOUS |
| Zdroj: | SPIE SECURITY DEFENCE 2019 SPIE SECURITY DEFENCE 2019, Sep 2019, Strasbourg, France. ⟨10.1117/12.2533178⟩ |
| DOI: | 10.1117/12.2533178⟩ |
| Popis: | Performing reliable target recognition in infrared imagery is a challenging problem due to the variation of the signatures of the targets caused by changes in the environment, the viewpoint or the state of the targets. Due to their state-of-the-art performance on several computer vision problems, Convolutional Neural Networks (CNNs) are particularly appealing in this context. However, CNNs may provide wrong classification results with high confidence. Robustness to disturbed inputs can be mitigated through the implementation of specific training strategies to improve classification performances. But they would generally require retraining or fine-tuning the CNN to face new forms of disturbed inputs. Besides, such strategies do not necessarily tackle novelty detection without training an auxiliary classifier. In this paper we propose two solutions to give the ability of a trained CNN to deal with both adversarial examples and novelty detection during inference. The first approach is based on one-class support vector machines (SVM) and the second one relies on the Local Outlier Factor (LOF) algorithm for example detection. We benchmark our contributions on SENSIAC database for a pre-trained network and evaluate how they may help mitigate false classifications on outliers and adversarial inputs. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|