Diogo Carneiro
Research Subjects
Research Interests
Diogo Carneiro has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Diana Teixeira e Silva
Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal
1 shared publication - Jaime Santos Cardoso
INESC TEC, Faculdade de Engenharia, Universidade do Porto, Porto, Portugal
1 shared publication - Ricardo Cruz
Faculty of Engineering, University of Porto, Porto, Portugal
1 shared publication - Tiago Gonçalves
Universidade do Porto
1 shared publication
Latest Publications
- Open Access
Two-Stage Framework for Faster Semantic Segmentation
Semantic segmentation consists of classifying each pixel according to a set of classes. Conventional models spend as much effort classifying easy-to-segment pixels as they do classifying hard-to-segment pixels. This is inefficient, especially when deploying to situations with computational constraints. In this work, we propose a framework wherein the model first produces a rough segmentation of the image, and then patches of the image estimated as hard to segment are refined. The framework is evaluated in four datasets (autonomous driving and biomedical), across four state-of-the-art architectures. Our method accelerates inference time by four, with additional gains for training time, at the cost of some output quality.
Open AccessTwo-Stage Framework for Faster Semantic Segmentation
Semantic segmentation consists of classifying each pixel according to a set of classes. Conventional models spend as much effort classifying easy-to-segment pixels as they do classifying hard-to-segment pixels. This is inefficient, especially when deploying to situations with computational constraints. In this work, we propose a framework wherein the model first produces a rough segmentation of the image, and then patches of the image estimated as hard to segment are refined. The framework is evaluated in four datasets (autonomous driving and biomedical), across four state-of-the-art architectures. Our method accelerates inference time by four, with additional gains for training time, at the cost of some output quality.