US 12,450,891 B2
Image classifier comprising a non-injective transformation
Didrik Nielsen, København K (DK); Emiel Hoogeboom, Amsterdam (NL); Kaspar Sakmann, Stuttgart (DE); Max Welling, Amsterdam (NL); and Priyank Jaini, Amsterdam (NL)
Assigned to ROBERT BOSCH GMBH, Stuttgart (DE)
Filed by Robert Bosch GmbH, Stuttgart (DE)
Filed on Jun. 11, 2021, as Appl. No. 17/345,702.
Claims priority of application No. 20183862 (EP), filed on Jul. 3, 2020.
Prior Publication US 2022/0012549 A1, Jan. 13, 2022
Int. Cl. G06V 10/82 (2022.01); G06F 18/211 (2023.01); G06F 18/214 (2023.01); G06F 18/2415 (2023.01); G06F 18/2431 (2023.01); G06F 18/25 (2023.01); G06N 3/048 (2023.01); G06N 3/08 (2023.01); G06V 10/764 (2022.01); G06V 10/77 (2022.01); G06V 10/776 (2022.01)
CPC G06V 10/82 (2022.01) [G06F 18/211 (2023.01); G06F 18/2155 (2023.01); G06F 18/2415 (2023.01); G06F 18/2431 (2023.01); G06F 18/25 (2023.01); G06N 3/048 (2023.01); G06N 3/08 (2013.01); G06V 10/764 (2022.01); G06V 10/7715 (2022.01); G06V 10/776 (2022.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method of training an image classifier, the image classifier being configured to classify an input image into a class from a set of classes, the method comprising the following steps:
accessing a training dataset, the training dataset including at least one labelled training image labelled with a training class from the set of classes and at least one unlabelled training image;
defining an inverse model for the image classifier, the inverse model configured to map output classes of the image classifier to input images, wherein the image classifier includes a set of transformations, the set of transformations including at least one deterministic and non-injective transformation, an inverse of the deterministic and non-injective transformation being approximated in the inverse model by a stochastic inverse transformation, the inverse model including trainable parameters, and sharing a plurality of the trainable parameters with the image classifier;
training the image classifier using a log-likelihood optimization, the training including:
selecting a training image from the training dataset,
applying the image classifier to the training image, including applying the deterministic and non-injective transformation to transformation inputs of the deterministic and non-injective transformation to obtain transformation outputs of the deterministic and non-injective transformation,
determining a likelihood contribution for the deterministic and non-injective transformation of the image classifier based on a probability that the stochastic inverse transformation of the inverse model generates the transformation inputs given the transformation outputs,
when the training image is the labelled training image, using the likelihood contribution to determine a log-likelihood for the labelled training image and its label according to a joint probability distribution of input images and classes determined by the image classifier,
when the training image is the unlabelled training image, using the determined likelihood contribution to determine a log-likelihood for the unlabelled training image according to a probability distribution of input images being generated by the inverse model; and
optimizing parameters of the image classifier to maximize the log-likelihood for the labelled training image occurring according to the joint probability distribution and optimizing parameters of the inverse model to maximize the log-likelihood for the unlabelled training image for the unlabelled training image occurring according to the probability distribution of input images being generated by the inverse model.