Verfahren zur Bestimmung der Codiererarchitektur eines Neuronalen Netzes

Details

Veröffentlichungs-Nr.

EP4033402

Aktenzeichen

EP21153462

Anmeldetag

26. Januar 2021

Veröffentlichung

27. Juli 2022

Rechtsraum

EP

IPC

G06F18/20G06V10/70G06V10/82G06V20/58G06N3/045G06N3/08G06N3/0464

Abstract

The invention relates to a method for determining the architecture of an encoder (2) of a convolutional neural network (1), the neural network (1) being configured to process multiple different image processing tasks (t1, t2, t3), the method comprising the steps of:- for each image processing task (t1, t2, t3)), calculating characteristic scale distribution based on training data (S10);- generating multiple encoder architecture candidates, each encoder architecture of said encoder architecture candidates comprising at least one shared encoder layer (SL) which provides computational operations for multiple image processing tasks and multiple branches (b1, b2, b3) which span over one or more encoder layers which provide at least partly different computational operations for said image processing tasks, wherein each branch (b1, b2, b3) is associated with a certain image processing task (t1, t2, t3) (S11);- calculating receptive field sizes of the encoder layers of said multiple encoder architectures (S12);- calculating multiple assessment measures, each assessment measure referring to a combination of a certain encoder architecture of said multiple encoder architectures and a certain image processing task (t1, t2, t3), each assessment measure including information regarding the quality of matching of characteristic scale distribution of the image processing task (t1, t2, t3) associated with the assessment measure to the receptive field sizes of the encoder layers of the encoder architecture associated with the assessment measure (S13);- comparing the calculated assessment measures and establishing a comparison result (S14); and- selecting an encoder architecture based on the comparison result (S15).

Anmelder

Firmen

AUMOVIO Autonomous Mobility Germany GmbH
Continental Autonomous Mobility Germany GmbH
Continental Automotive GmbH

Land

🇩🇪 Deutschland

Fachgebiete