Oberseminar Bildverarbeitung, Computersehen und Computergraphik

Prof. Dr.-Ing. Thomas Brox, Prof. Dr.-Ing Matthias Teschner, apl. Prof. Dr. Olaf Ronneberger

Nächste Termine:

Vorankündigung (Aushang):

Freitag, 10.11.2017, 14:00 hst
Geb. 80 (AIS), Seminarraum

Herr Sudhanshu Mittal
Institut für Informatik, Universität Freiburg

berichtet über die Ergebnisse seiner Masterarbeit:

Semi-supervised Learning for Real-world Object Recognition using Adversarial Autoencoders

For many real-world applications, labeled data can be costly to obtain. Semi-supervised learning methods make use of substantially available unlabeled data along with few labeled samples. Most of the latest work on semi-supervised learning for image classification show performance on standard machine learning datasets like MNIST, SVHN, etc. In this work, we propose a convolutional adversarial autoencoder architecture for real-world data. We demonstrate the application of this architecture for semi-supervised object recognition. We show that our approach can learn from limited labeled data and outperform fully-supervised CNN baseline method by about 4% on real-world datasets. We also achieve competitive performance on the MNIST dataset compared to state-of-the-art semi-supervised learning techniques. To spur research in this direction, we compiled two real-world datasets: Internet (WIS) dataset and Real-world (RW) dataset which consists of more than 20K labeled samples each, comprising of small household objects. We also show a possible application of this method for online learning in robotics.

Bitte beachten Sie die Zeit und den Ort!

Interessenten sind herzlich eingeladen. Weitere Informationen bei: Prof. Dr.-Ing. Thomas Brox, Tel: 0761/203-8261