US 12,242,933 B1
Adaptive model for vehicle processing of images
Mihir Sathe, San Diego, CA (US); and Jesse Daniels, San Diego, CA (US)
Assigned to Lytx, Inc., San Diego, CA (US)
Filed by Lytx, Inc., San Diego, CA (US)
Filed on Sep. 3, 2021, as Appl. No. 17/466,156.
Int. Cl. G06N 20/00 (2019.01)
CPC G06N 20/00 (2019.01) 18 Claims
OG exemplary drawing
 
1. A system, comprising:
an interface configured to:
receive a general training set and a set of specific data sets;
a processor configured to:
train a back end model using the general training set, wherein the general training set comprises a general image training set;
combine the back end model with a first front end model to create a general combined model;
train the general combined model with the set of specific data sets;
freeze back end weights of the back end model in the general combined model and combine the back end model with a first specific front end model to create a first specific model;
train the first specific model with a first specific data set of the set of specific data sets, wherein the set of specific data sets includes one or more specific data sets associated with a category, and wherein the category is defined by one or more of the following: a location, a weather condition, a vehicle type, a traffic level, a speed level, a signage type, a country name, a state name, or a county name; and
provide the first specific model.