Towards Open Set Deep Networks: Supplemental
نویسندگان
چکیده
In this supplement, we provide we provide additional material to further the reader as understanding of the work on Open Set Deep Networks, Mean Activation Vectors, Open Set Recognition and OpenMax algorithm. We present additional experiments on ILSVRC 2012 dataset. First we present experiments to illustrate performance of OpenMax for various parameters of EVT calibration (Alg. 1, main paper) followed by sensitivity of OpenMax to total number of “top classes” (i.e. α in Alg. 2, main paper) to consider for recalibrating SoftMax scores. We then present different distance measures namely Euclidean and cosine distance used for EVT calibration. We then illustrate working of OpenMax with qualitative examples for open set evaluation performed during the testing phase. Finally, we illustrate the distribution of Mean Activation Vectors with a class confusion map.
منابع مشابه
Estimation of Hand Skeletal Postures by Using Deep Convolutional Neural Networks
Hand posture estimation attracts researchers because of its many applications. Hand posture recognition systems simulate the hand postures by using mathematical algorithms. Convolutional neural networks have provided the best results in the hand posture recognition so far. In this paper, we propose a new method to estimate the hand skeletal posture by using deep convolutional neural networks. T...
متن کاملDriving Digital Rock towards Machine Learning: predicting permeability with Gradient Boosting and Deep Neural Networks
We present a research study aimed at testing of applicability of machine learning techniques for prediction of permeability of digitized rock samples. We prepare a training set containing 3D images of sandstone samples imaged with X-ray microtomography and corresponding permeability values simulated with Pore Network approach. We also use Minkowski functionals and Deep Learning-based descriptor...
متن کاملA Geometric Perspective on the Robustness of Deep Networks
Deep neural networks have recently shown impressive classification performance on a diverse set of visual tasks. When deployed in real-world (noise-prone) environments, it is equally important that these classifiers satisfy robustness guarantees: small perturbations applied to the samples should not yield significant losses to the performance of the predictor. The goal of this paper is to discu...
متن کاملGenerative OpenMax for Multi-Class Open Set Classification
We present a conceptually new and flexible method for multi-class open set classification. Unlike previous methods where unknown classes are inferred with respect to the feature or decision distance to the known classes, our approach is able to provide explicit modelling and decision score for unknown classes. The proposed method, called Generative OpenMax (G-OpenMax), extends OpenMax by employ...
متن کاملOpen-set Plant Identification Using an Ensemble of Deep Convolutional Neural Networks
Open-set recognition, a challenging problem in computer vision, is concerned with identification or verification tasks where queries may belong to unknown classes. This work describes a fine-grained plant identification system consisting of an ensemble of deep convolutional neural networks, within an open-set identification framework. Two wellknown deep learning architectures of VGGNet and Goog...
متن کامل