Intersection over Union with smoothing for bounding box regression

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F23%3AA2402KWI" target="_blank" >RIV/61988987:17610/23:A2402KWI - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-031-43078-7_17" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-43078-7_17</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-43078-7_17" target="_blank" >10.1007/978-3-031-43078-7_17</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Intersection over Union with smoothing for bounding box regression

Popis výsledku v původním jazyce

We focus on the construction of a loss function for the bounding box regression. The Intersection over Union (IoU) metric is improved to converge faster, to make the surface of the loss function smooth and continuous over the whole searched space, and to reach a more precise approximation of the labels. The main principle is adding a smoothing part to the original IoU, where the smoothing part is given by a linear space with values that increases from the ground truth bounding box to the border of the input image, and thus covers the whole spatial search space. We show the motivation and formalism behind this loss function and experimentally prove that it outperforms IoU, DIoU, CIoU, and SIoU by a large margin. We experimentally show that the proposed loss function is robust with respect to the noise in the dimension of ground truth bounding boxes. The reference implementation is available at gitlab.com/irafm-ai/smoothing-iou.

Název v anglickém jazyce

Intersection over Union with smoothing for bounding box regression

Popis výsledku anglicky

We focus on the construction of a loss function for the bounding box regression. The Intersection over Union (IoU) metric is improved to converge faster, to make the surface of the loss function smooth and continuous over the whole searched space, and to reach a more precise approximation of the labels. The main principle is adding a smoothing part to the original IoU, where the smoothing part is given by a linear space with values that increases from the ground truth bounding box to the border of the input image, and thus covers the whole spatial search space. We show the motivation and formalism behind this loss function and experimentally prove that it outperforms IoU, DIoU, CIoU, and SIoU by a large margin. We experimentally show that the proposed loss function is robust with respect to the noise in the dimension of ground truth bounding boxes. The reference implementation is available at gitlab.com/irafm-ai/smoothing-iou.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Advances in Computational Intelligence. IWANN 2023. Lecture Notes in Computer Science, vol 14135

ISBN

978-3-031-43077-0

ISSN

03029743

e-ISSN

—

Počet stran výsledku

11

Strana od-do

206-216

Název nakladatele

Springer, Cham

Místo vydání

—

Místo konání akce

Ponta Delgada, Portugal

Datum konání akce

19. 6. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—