Dynamically Adaptive Instance Normalization and Attention-Aware Incremental Meta-Learning for Generalizable Person Re-identification
Lists
Only you see this
Abstract
Domain generalization person re-identification (DG-ReID) aims to train a generalizable model over several source domains that can perform well on unseen target domains, which makes the DG-ReID task challenging since the model is not allowed to access any target data during training. The classic meta-learning method, which simulates the train-test process of DG-ReID task, is a popular and effective way for DG-ReID. Nevertheless, the method still suffers from the unstable meta-optimization problem. We thus propose a novel Dynamically Adaptive Instance Normalization and Attention-Aware Incremental Meta-Learning (DAIML) optimization method to effectively address this issue. In addition, most existing DG-ReID studies generally utilize Instance Normalization (IN) to learn domain-irrelevant features for eliminating domain shift, which may lead to the removal of effective domain-specific discriminative information that is usually useful to enhance the discriminability of a particular source. Therefore, we propose a dynamically adaptive IN (DAIN) that can balance well the learning of domain-invariant representations and domain-specific discriminative features. Furthermore, we apply channel attention and spatial attention to the proposed DAIN for further improving the domain-irrelevant discriminative information. Extensive experiments demonstrate the effectiveness of our proposed method on several DG-ReID datasets.
BibTeX
@inproceedings{gong2023dynamically,
author = {Tiantian Gong and Kaixiang Chen and Junsheng Wang and Liyan Zhang},
title = {{Dynamically Adaptive Instance Normalization and Attention-Aware Incremental Meta-Learning for Generalizable Person Re-identification}},
booktitle = {ICME},
year = {2023},
url = {https://openreview.net/forum?id=60CqcWABqe},
}Loading related content...