Timeline for YOLOv1 algorithm - how to determine predictor responsibility
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 19, 2021 at 15:50 | vote | accept | monolith | ||
| Dec 31, 2020 at 1:33 | answer | added | Javier TG | timeline score: 1 | |
| Nov 12, 2020 at 21:08 | comment | added | Ismael EL ATIFI | DETR (another object detection model whose paper is at arxiv.org/abs/2005.12872) uses the Hungarian algorithm to do the matching of GT boxes and predictors. Quote from the paper : "The usual solution is to design a loss based on the Hungarian algorithm [20], to find a bipartite matching between ground-truth and prediction." | |
| Nov 12, 2020 at 20:53 | comment | added | Ismael EL ATIFI | I would advise to look at some implementations to see by yourself. There is several YoloV1 github repos. There are many potential matching methods actually. You could even use some optimal linear bipartite matching algorithm like the Hungarian algorithm (to find a matching that minimizes the sum of the costs). | |
| Nov 12, 2020 at 17:20 | review | First posts | |||
| Nov 12, 2020 at 22:20 | |||||
| Nov 12, 2020 at 17:14 | history | asked | monolith | CC BY-SA 4.0 |