Decentralised Person Re-Identification with Selective Knowledge Aggregation

by   Shitong Sun, et al.

Existing person re-identification (Re-ID) methods mostly follow a centralised learning paradigm which shares all training data to a collection for model learning. This paradigm is limited when data from different sources cannot be shared due to privacy concerns. To resolve this problem, two recent works have introduced decentralised (federated) Re-ID learning for constructing a globally generalised model (server)without any direct access to local training data nor shared data across different source domains (clients). However, these methods are poor on how to adapt the generalised model to maximise its performance on individual client domain Re-ID tasks having different Re-ID label spaces, due to a lack of understanding of data heterogeneity across domains. We call this poor 'model personalisation'. In this work, we present a new Selective Knowledge Aggregation approach to decentralised person Re-ID to optimise the trade-off between model personalisation and generalisation. Specifically, we incorporate attentive normalisation into the normalisation layers in a deep ReID model and propose to learn local normalisation layers specific to each domain, which are decoupled from the global model aggregation in federated Re-ID learning. This helps to preserve model personalisation knowledge on each local client domain and learn instance-specific information. Further, we introduce a dual local normalisation mechanism to learn generalised normalisation layers in each local model, which are then transmitted to the global model for central aggregation. This facilitates selective knowledge aggregation on the server to construct a global generalised model for out-of-the-box deployment on unseen novel domains. Extensive experiments on eight person Re-ID datasets show that the proposed approach to decentralised Re-ID significantly outperforms the state-of-the-art decentralised methods.


page 1

page 4


Decentralised Learning from Independent Multi-Domain Labels for Person Re-Identification

Deep learning has been successful for many computer vision tasks due to ...

Federated and Generalized Person Re-identification through Domain and Feature Hallucinating

In this paper, we study the problem of federated domain generalization (...

Deep Learning Prototype Domains for Person Re-Identification

Person re-identification (re-id) is the task of matching multiple occurr...

Optimizing Performance of Federated Person Re-identification: Benchmarking and Analysis

The increasingly stringent data privacy regulations limit the developmen...

Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice

Contemporary person re-identification (Re-ID) methods usually require ac...

Federated Zero-Shot Learning with Mid-Level Semantic Knowledge Transfer

Conventional centralised deep learning paradigms are not feasible when d...

Semantically Selective Augmentation for Deep Compact Person Re-Identification

We present a deep person re-identification approach that combines semant...

Please sign up or login with your details

Forgot password? Click here to reset