Projects per year
Abstract
Deep neural networks paved the way for significant improvements in image visual categorization during the last years. However, even though the tasks are highly varying, differing in complexity and difficulty, existing solutions mostly build on the same architectural decisions. This also applies to the selection of activation functions (AFs), where most approaches build on Rectified Linear Units (ReLUs). In this paper, however, we show that the choice of a proper AF has a significant impact on the classification accuracy, in particular, if fine, subtle details are of relevance. Therefore, we propose to model the degree of absence and the degree presence of features via the AF by using piece-wise linear functions, which we refer to as L*ReLU. In this way, we can ensure the required properties, while still inheriting the benefits in terms of computational efficiency from ReLUs. We demonstrate our approach for the task of Fine-grained Visual Categorization (FGVC), running experiments on seven different benchmark datasets. The results do not only demonstrate superior results but also that for different tasks, having different characteristics, different AFs are selected.
Original language | English |
---|---|
Title of host publication | Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020 |
Pages | 1207-1216 |
Number of pages | 10 |
ISBN (Electronic) | 978-1-7281-6553-0 |
DOIs | |
Publication status | Published - 1 Mar 2020 |
Event | wacv2020: WACV 2020 - Snowmass Village, United States Duration: 1 Mar 2020 → 5 Mar 2020 |
Publication series
Name | Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020 |
---|
Conference
Conference | wacv2020 |
---|---|
Abbreviated title | WACV 2020 |
Country/Territory | United States |
City | Snowmass Village |
Period | 1/03/20 → 5/03/20 |
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
- Computer Science Applications
Fields of Expertise
- Information, Communication & Computing
Projects
- 1 Finished
-
SISDAL - Semantic Image Segmentation by Deep Active Learning in medical imaging applications
1/04/19 → 30/09/21
Project: Research project