Person Re-Identification ANN Adaptation With Support-Set Distillation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for adapting an artificial neural network (ANN) model trained on a source domain to a target domain suffer from catastrophic forgetting and domain shift, especially when data from the target domain is limited and biased, and require large data storage which is impractical or prohibited.

Innovation Solution

A method involving multiple iterations of an adaptation phase that includes constructing a support set of similar source images, using a teacher model for knowledge distillation, and calculating domain shift costs to minimize global costs, thereby updating the ANN model weights to adapt to the target domain without needing large data storage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If online unsupervised domain adaptation is performed with limited target domain data, then the model can adapt to the target domain without gathering large amounts of data, but catastrophic forgetting occurs and the model forgets knowledge acquired previously

Engineering Contradiction:
Improveadaptability to target domainVSAvoidcatastrophic forgetting
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The method constructs a support set from source domain images that are similar to the target domain images before performing domain adaptation. This preliminary construction of relevant source data provides a foundation that guides the adaptation process, enabling the model to adapt to the target domain while maintaining knowledge from the source domain through the similarity-based selection mechanism

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The support set acts as an intermediary between the source domain and target domain. It is constructed from source images that are similar to target images and serves as a bridge during the domain adaptation process, allowing knowledge transfer while preventing catastrophic forgetting by maintaining relevant source domain characteristics

Inventive Principle:
Principle #24Intermediary (Mediator)

2Quantity of substance

If online unsupervised domain adaptation is performed with limited target domain data, then data storage requirements are reduced, but domain shift occurs since the model accesses a small and possibly biased subset of target domain data

Engineering Contradiction:
Improvedata storage requirementVSAvoiddomain shift
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The support set is constructed in advance from source domain images that are similar to the target domain images. This preliminary action selects source images that will be most useful for domain adaptation, reducing the need to store large amounts of target domain data while minimizing domain shift through similarity-based selection

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The method changes the parameter of data selection from random or uniform sampling to similarity-based sampling. By constructing the support set using a similarity function that measures the relationship between source and target images, the method adapts the data selection parameter to reduce domain shift while maintaining reduced storage requirements

Inventive Principle:
Principle #35Parameter changes

3Reliability

If the model is retrained on the target domain, then the model achieves good performance on the target domain, but it requires collecting and annotating data from the target domain which is not practical or possible

Engineering Contradiction:
Improveperformance on target domainVSAvoiddata collection and annotation
Core Design Contradiction:
ReliabilityVSEase of manufacture

Solution Approach 1:

The support set constructed from source domain images serves as an intermediary that eliminates the need for target domain data collection and annotation. By selecting source images that are similar to target images and using them in the domain adaptation process, the method achieves good target domain performance without requiring practical data collection and annotation efforts

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The method creates a copy of relevant source domain data (the support set) that is similar to the target domain. Instead of collecting and annotating actual target domain data, the method copies and adapts source domain images that have similar characteristics, achieving the same effect without the practical burden of target domain data collection

Inventive Principle:
Principle #26Copying

Data Source

PatentEP4421756B1Method, device and computer program for adapting an ann model for person re-identification on a target domain
Publication Date: 2025.10.29 BULL SA
  • EP4421756B1 patent drawingFigure 1
  • EP4421756B1 patent drawingFigure 2
  • EP4421756B1 patent drawingFigure 3

AI summary

The invention relates to a method (100) for adapting an ANN model, previously trained for person re-identification on a source domain (SD), on a target domain, said method (100) comprising several iterations of an adaptation phase (110) comprising: -constructing (120) a support set, by selecting from said source domain (SD) images similar to images in a new set of images received from the target domain (NTSi), -several iterations of a training step (130) comprising the following steps: ▪ determining (140) a rei-id cost on said new set of images (NTSi); ▪ determining (150) a Knowledge Distillation, KD, cost, with respect to a teacher model, on a support set (SSi-i) constructed during a previous iteration of the adaptation phase, ▪ updating (162) the ANN; ▪ updating (164) the teacher model. The invention further relates to a computer program and a device configured to carry out such a method, and to an artificial neural network trained with such a method.