PhD thesis defense: Jordi Pont-Tuset

Jordi Pont defends his PhD thesis entitled Image Segmentation Evaluation and Its Application to Object Detection
Wednesday February 19th, 11h, Aula de Telensenyament, B3 building, 1st floor

Dissertation summary:
The first two parts of this Thesis are focused on the study of the supervised evaluation of image segmentation algorithms. Supervised in the sense that the segmentation results are compared to a human-made annotation, known as ground truth, by means of different measures of similarity. We review, strucure, and deduplicate the measures available in the literature, and we provide a new precision-recall framework fo evaluating image segmentation. To compare the quality of the measures, we propose a set of meta-measures, both from a qualitative and a quantitative point of view.

The third part of this Thesis moves from the evaluation of image segmentation to its application to object detection. In particular, we build on the conclusions extracted in the first parts to generate segmented object candidates. Given a set of hierarchies, we build the pairs and triplets of regions, we learn to combine the set from each hierarchy, and we rank them using low-level and mid-level cues. We conduct an extensive experimental validation that show that our method outperforms the state of the art in many metrics tested.