Method for configuring neural network model

Abstract

The invention relates to a computer-implemented method (100) for configuring a neural network model, wherein the method comprises the following steps: providing (102) a neural network model; splitting (104) the neural network model into a first portion and a second portion, the second portion comprising a first head for classifying a first type of classification data and a second head for classifying the second type of classification data; pre-processing (106), in a training phase, the second type of classification data in the first portion, processing (108) the pre-processed second type of classification data in the first and second heads and determining a first result of the processing of first type of classification data in the first head and a second result of the processing of first type of classification data in the second head; calculating (110) the consistency between the first result and the second result; and configuring (112) the neural network model by updating a value of at least one parameter of the second head based on the calculated consistency.

Description

technical field [0001] The invention relates to a computer-implemented method for configuring a neural network model, a neural network, a neural network use for configuring a neural network model, a computer program element and a computer readable medium. Background technique [0002] Domain adaptation is a field of machine learning that aims to exploit the knowledge of a given domain, called the source domain, where the knowledge is transferred into another domain, called the target domain. This is a special case of so-called transfer learning, where the given task for both domains is the same, but the target dataset may contain a distribution shift compared to the source dataset. An example of this problem is object recognition, for example, in daytime and nighttime images of a vehicle's surroundings. [0003] A common learning approach in source and target domains is to try to modify the internal representations of the data so that they are as similar as possible to both...

AI Technical Summary

Problems solved by technology

However, a naive mixture of target and source labels is problematic because it does not indicate to the network that the target is more important than the source during training

For example due to some limitations it cannot prioritize target label patterns whenever it has to choose a specified network whose label pattern should be remembered

In extreme cases where multiple source labels are available, this can severely impact target accuracy

Images