US 2024/0404258 A1 · AUTOMATIC EFFICIENT SMALL MODEL SELECTION FOR MONOCULAR DEPTH ESTIMATION

Abstract

Systems and methods are described for selecting models to perform monocular depth estimation. A computing device may receive a plurality of image and select an image from the plurality of images to evaluate a first machine-learning model and a plurality of machine-learning models are smaller than the first machine-learning model. The computing device may process the image using a first machine-learning model to generate a first predicted result. The computing device may also process the image using the plurality of machine-learning models to generate at least a second predicted result and a third test data set. The computing device may select a second machine-learning model from the plurality of machine-learning models based on a comparison of the first predicted result with the at least the second predicted result and the third test data set. The computing device may then process the plurality of images using the second machine-learning model.

Claims20

Dependent claims

A computer-implemented method comprising:

receiving a plurality of images;
selecting one or more images from the plurality of images;
processing the one or more images using a first machine-learning model to generate a first predicted result;
processing the one or more images using a plurality of machine-learning models to generate at least a second predicted result and a third test data set, wherein the first machine-learning model is larger than the plurality of machine-learning models;
selecting, based on a comparison of the first predicted result with the at least the second predicted result and the third test data set, a second machine-learning model from the plurality of machine-learning models;
and
processing the plurality of images using the second machine-learning model.

4 more elements

A system comprising:

one or more processors;
and
a non-transitory computer-readable medium storing instructions that when executed by the one or more processors, cause the one or more processors to:
receive a plurality of image;
select one or more images from the plurality of images;
process the one or more images using a first machine-learning model to generate a first predicted result;
process the one or more images using a plurality of machine-learning models to generate at least a second predicted result and a third test data set, wherein the first machine-learning model is larger than the plurality of machine-learning models;
select, based on a comparison of the first predicted result with the at least the second predicted result and the third test data set, a second machine-learning model from the plurality of machine-learning models;
and
process the plurality of images using the second machine-learning model.

7 more elements

A non-transitory computer-readable medium storing instructions that when executed by one or more processors, cause the one or more processors to:

receive a plurality of image;
select one or more images from the plurality of images;
process the one or more images using a first machine-learning model to generate a first predicted result;
process the one or more images using a plurality of machine-learning models to generate at least a second predicted result and a third test data set, wherein the first machine-learning model is larger than the plurality of machine-learning models;
select, based on a comparison of the first predicted result with the at least the second predicted result and the third test data set, a second machine-learning model from the plurality of machine-learning models;
and
process the plurality of images using the second machine-learning model.

4 more elements

Dependencies are inferred from the claim text.

Automatic efficient small model selection for monocular depth estimation

Life of this patent

Automatic efficient small model selection for monocular depth estimation

Life of this patent

Abstract

Claims20