Logo des Repositoriums

Auflistung nach Schlagwort "transfer learning"

1 - 3 von 3
  • Textdokument
    Application-specific quality metrics for the assessment of data for deep learning from large datasets
    (INFORMATIK 2022, 2022) Götte,Gesa Marie; Thielert,Bonito Steffen; Herzog,Andreas
    Application-specific quality metrics support getting suitable data from large databases to pre-train deep neural networks or getting good statistical measures. Especially when using high-dimensional or multimodal sensor data from industrial processes the small amount of training examples from each device or plant must be supplemented by additional data. We present a system for the definition of application-specific metrics in a model composed of statistical functions and neural networks. Further, we introduce a business model for using this system for the interaction of data providers with their customers. In order to obtain suitable data, the user sends his request to the data provider in the form of a quality metric model and gets back the best fitted data. Our system helps the user to define the model through examples and by setting the model parameters through genetic algorithms.
  • Textdokument
    Deep Convolutional Neural Networks for Pose Estimation in Image-Graphics Search
    (INFORMATIK 2017, 2017) Eberts, Markus; Ulges, Adrian
    Deep Convolutional Neural Networks (CNNs) have recently been highly successful in various image understanding tasks, ranging from object category recognition over image classification to scene segmentation. We employ CNNs for pose estimation in a cross-modal retrieval system, which -given a photo of an object -allows users to retrieve the best match from a repository of 3D models. As our system is supposed to display retrieved 3D models from the same perspective as the query image (potentially with virtual objects blended over), the pose of the object relative to the camera needs to be estimated. To do so, we study two CNN models. The first is based on end-to-end learning, i.e. a regression neural network directly estimates the pose. The second uses transfer learning with a very deep CNN pre-trained on a large-scale image collection. In quantitative experiments on a set of 3D models and real-world photos of chairs, we compare both models and show that while the end-to-end learning approach performs well on the domain it was trained on (graphics) it suffers from the capability to generalize to a new domain (photos). The transfer learning approach on the other hand handles this domain drift much better, resulting in an average angle deviation from the ground truth angle of about 14 degrees on photos.
  • Konferenzbeitrag
    A robust fingerprint presentation attack detection method against unseen attacks through adversarial learning
    (BIOSIG 2020 - Proceedings of the 19th International Conference of the Biometrics Special Interest Group, 2020) Pereira, Joao Afonso; Sequeira, Ana F.; Pernes, Diogo; Cardoso, Jaime S.
    Fingerprint presentation attack detection (PAD) methods present a stunning performance in current literature. However, the fingerprint PAD generalisation problem is still an open challenge requiring the development of methods able to cope with sophisticated and unseen attacks as our eventual intruders become more capable. This work addresses this problem by applying a regularisation technique based on an adversarial training and representation learning specifically designed to to improve the PAD generalisation capacity of the model to an unseen attack. In the adopted approach, the model jointly learns the representation and the classifier from the data, while explicitly imposing invariance in the high-level representations regarding the type of attacks for a robust PAD. The application of the adversarial training methodology is evaluated in two different scenarios: i) a handcrafted feature extraction method combined with a Multilayer Perceptron (MLP); and ii) an end-to-end solution using a Convolutional Neural Network (CNN). The experimental results demonstrated that the adopted regularisation strategies equipped the neural networks with increased PAD robustness. The adversarial approach particularly improved the CNN models’ capacity for attacks detection in the unseen-attack scenario, showing remarkable improved APCER error rates when compared to state-of-the-art methods in similar conditions.