Abstract
Food trackers are tools that recognize foods using their images. In the core of these tools there is usually a neural network that performs the classification. Neural networks are highly expressive models that need a large dataset to generalize well. Since it is hard to collect a training set that captures most of realistic situations in real world, there is usually a shift between the training set and the actual test set. This potentially reduces the performance of the network. In this paper, we propose a method based on self-training to perform unsupervised domain adaptation in the task of food classification. Our method takes into account the uncertainty of predictions instead of probability scores to assign pseudo-labels. Our experiments on the Food-101 and the UPMC-101 datasets show that the proposed method produces more accurate results compared to Tri-training method which had previously surpassed other domain adaptation methods.
Original language | English |
---|---|
Title of host publication | VISIGRAPP 2019 -Proceedings of the 14th International Joint Conference on Computer Vision |
Editors | Alain Tremeau, Giovanni Maria Farinella, Jose Braz |
Publisher | SciTePress |
Pages | 143-154 |
Volume | 5 |
ISBN (Electronic) | 978-989758354-4 |
DOIs | |
Publication status | Published - 2019 |
Externally published | Yes |
Event | 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications: VISIGRAPP 2019 - Prague, Czech Republic Duration: 25 Feb 2019 → 27 Feb 2019 |
Conference
Conference | 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications |
---|---|
Abbreviated title | VISAPP 2019 |
Country/Territory | Czech Republic |
City | Prague |
Period | 25/02/19 → 27/02/19 |