Intersection over Union with smoothing for bounding box regression

Result code in 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>

Result on the web

<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>

Result language

angličtina

Original language name

Intersection over Union with smoothing for bounding box regression

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2023

Confidentiality

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

Article name in the collection

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

ISBN

978-3-031-43077-0

ISSN

03029743

e-ISSN

—

Number of pages

11

Pages from-to

206-216

Publisher name

Springer, Cham

Place of publication

—

Event location

Ponta Delgada, Portugal

Event date

Jun 19, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—