Meeting date: 18-05-2023 (10h30)

Summary

The state of the art is essentially complete, with the exception of the deep learning models section, where I have some questions.

I talked to Pedro about the videos he recorded in Aveiro, but he doesn't have the raw version.

In Jetson, for some reason the segmentation is not working, even though it doesn't give any errors related to the problem. I will try to fix this during the next week.

348360353_784449863305089_1158479081408212738_n.png

Last week's misunderstanding with yolo (Yolo with coupled vs decoupled heads)

https://paperswithcode.com/method/yolox

https://www.v7labs.com/blog/yolo-object-detection

https://www.researchgate.net/figure/The-architecture-of-the-YOLO-detection-head-a-YOLO-detection-head-uses-the-feature-maps_fig1_362680027

For other questions:

Stanford University: https://cs330.stanford.edu/

https://slideslive.com/38917690/multitask-learning-in-the-wilderness

GATO: https://arxiv.org/pdf/2205.06175.pdf


Next week (dd-mm)