Samsung patents method to train object estimation models using cross-correlation
Samsung describes a method for training a neural network model to estimate objects by comparing its output with a second, already-trained model. The process calculates a specific error value, or loss, based on how well the two models' feature vectors align, including data from augmented inputs.
In the filing’s own words
A method and apparatus with object estimation model training is provided. The method include generating a cross-correlation loss based on a first feature vector, generated using an interim first neural network (NN) model provided an input based on first input data about a target object, and a second feature vector generated using a trained second neural network provided another input based on second input data about the target object; and generating a trained first NN model, including training the interim first NN model based on the cross-correlation loss.
What exactly they claim (claim 1)
1. A processor-implemented method, comprising: generating a cross-correlation loss based on a first feature vector, generated using an interim first neural network (NN) model provided an input based on first input data about a target object, and a second feature vector generated using a trained second neural network provided another input based on second input data about the target object, and based on a first target feature vector obtained based on the first feature vector and a first additional feature vector, and a second target feature vector obtained based on the second feature vector and a second additional feature vector, the first additional feature vector and the second additional feature vector being obtained based on data augmentation; and generating a trained first NN model, including training the interim first NN model based on the cross-correlation loss.
Facts
- Company
- Samsung (SAMSUNG ELECTRONICS CO., LTD.)
- Official title
- METHOD AND APPARATUS WITH OBJECT ESTIMATION MODEL TRAINING
- Publication number
- US20260289311A1
- Application number
- 19696471
- Filed
- Jun 3, 2026
- Published
- Sep 24, 2026
- Inventors
- 2
- Claims
- 20
Classified under
G06N 3/08 Physics & computingMore from Samsung in AI & software
- Samsung patents tool to erase objects from photos using AI Sep 24, 2026
- Samsung patents drawing objects into photos with AI Oct 15, 2026
- Samsung patents AI that creates personalized exercise videos Sep 10, 2026
- Samsung patents AI summaries for paused TV shows based on your viewing habits Sep 24, 2026
- Samsung patents turning chat conversations into image prompts Oct 1, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.