Selecting influential examples: Active learning with expected model output changes

A Freytag, E Rodner, J Denzler - … September 6-12, 2014, Proceedings, Part …, 2014 - Springer
In this paper, we introduce a new general strategy for active learning. The key idea of our
approach is to measure the expected change of model outputs, a concept that generalizes …

One-class classification with gaussian processes

M Kemmler, E Rodner, ES Wacker, J Denzler - Pattern recognition, 2013 - Elsevier
Detecting instances of unknown categories is an important task for a multitude of problems
such as object recognition, event detection, and defect localization. This article investigates …

Local novelty detection in multi-class recognition problems

P Bodesheim, A Freytag, E Rodner… - 2015 IEEE Winter …, 2015 - ieeexplore.ieee.org
In this paper, we propose using local learning for multiclass novelty detection, a framework
that we call local novelty detection. Estimating the novelty of a new sample is an extremely …

Active learning and discovery of object categories in the presence of unnameable instances

C Kading, A Freytag, E Rodner… - Proceedings of the …, 2015 - openaccess.thecvf.com
Current visual recognition algorithms are" hungry" for data but massive annotation is
extremely costly. Therefore, active learning algorithms are required that reduce labeling …

Change detection using high resolution remote sensing images based on active learning and Markov random fields

H Yu, W Yang, G Hua, H Ru, P Huang - Remote Sensing, 2017 - mdpi.com
Change detection has been widely used in remote sensing, such as for disaster assessment
and urban expansion detection. Although it is convenient to use unsupervised methods to …

GPU optimization of the SGM stereo algorithm

I Haller, S Nedevschi - Proceedings of the 2010 IEEE 6th …, 2010 - ieeexplore.ieee.org
GPU hardware architectures have evolved into a suitable platform for the hardware
acceleration of complex computing tasks. Stereo vision is one such task where acceleration …

Active online anomaly detection using dirichlet process mixture model and gaussian process classification

J Varadarajan, R Subramanian, N Ahuja… - 2017 IEEE Winter …, 2017 - ieeexplore.ieee.org
We present a novel anomaly detection (AD) system for streaming videos. Different from prior
methods that rely on unsupervised learning of clip representations, that are usually coarse in …

Gaussian process for predicting CPU utilization and its application to energy efficiency

DM Bui, HQ Nguyen, YI Yoon, SI Jun, MB Amin… - Applied Intelligence, 2015 - Springer
For the past ten years, Gaussian process has become increasingly popular for modeling
numerous inferences and reasoning solutions due to the robustness and dynamic features …

Temporal self-similarity for appearance-based action recognition in multi-view setups

M Körner, J Denzler - Computer Analysis of Images and Patterns: 15th …, 2013 - Springer
We present a general data-driven method for multi-view action recognition relying on the
appearance of dynamic systems captured from different viewpoints. Thus, we do not depend …

Decoding affect in videos employing the MEG brain signal

MK Abadi, M Kia, R Subramanian… - 2013 10th IEEE …, 2013 - ieeexplore.ieee.org
This paper presents characterization of affect (valence and arousal) using the
Magnetoencephalogram (MEG) brain signal. We attempt single-trial classification of movie …