US 12,469,271 B2
Training neural networks with a lesser requirement for labelled training data
Piyapat Saranrittichai, Nuremberg (DE); Andres Mauricio Munoz Delgado, Schoenaich (DE); Chaithanya Kumar Mummadi, Pittsburgh, PA (US); Claudia Blaiotta, Stuttgart (DE); and Volker Fischer, Renningen (DE)
Assigned to ROBERT BOSCH GMBH, Stuttgart (DE)
Filed by Robert Bosch GmbH, Stuttgart (DE)
Filed on Apr. 28, 2023, as Appl. No. 18/309,335.
Claims priority of application No. 22172172 (EP), filed on May 6, 2022.
Prior Publication US 2023/0360387 A1, Nov. 9, 2023
Int. Cl. G06V 10/82 (2022.01); G06V 10/46 (2022.01); G06V 10/54 (2022.01); G06V 10/56 (2022.01); G06V 10/60 (2022.01); G06V 20/56 (2022.01); G06V 20/58 (2022.01)
CPC G06V 10/82 (2022.01) [G06V 10/46 (2022.01); G06V 10/54 (2022.01); G06V 10/56 (2022.01); G06V 10/60 (2022.01); G06V 20/582 (2022.01); G06V 20/588 (2022.01); G06V 2201/07 (2022.01)] 18 Claims
OG exemplary drawing
 
1. A method for training a neural network for determining, from an input record of measurement data, a task output with respect to a given task, the neural network including:
an encoder network that is configured to map the input record to a representation, wherein the representation includes multiple independent components;
one or more task head networks that are configured to map representation components of the input record to the task output; and
an association network configured to provide, to each task head network of the one of more task head networks, a linear combination of those of the representation components of the input record x that are relevant for the task of the respective task head network,
the method comprising the following steps:
providing unlabeled and/or labelled encoder training records of measurement data;
training the encoder network to map encoder training records to representations towards a goal that the representations, and/or or one or more work products derived from the representations:
based on the representation being derived from an unlabeled encoder training record, fulfil a self-consistency condition that does not rely on ground truth, and
based on the representation being derived from a labelled encoder training record, correspond to the ground truth with which the encoder training record is labelled;
providing task training records that are labelled with ground truth; and
training the association network and the one or more task head networks towards a goal that, when the task training record is mapped to a representation using the encoder network, and the representation is mapped to a task output by a combination of the association network and the task head networks, a so-obtained task output corresponds to the ground truth with which the training record is labelled, as measured by a task loss function.