TY  - CONF
AU  - Kai Wang
AU  - Chenshen Wu
AU  - Andrew Bagdanov
AU  - Xialei Liu
AU  - Shiqi Yang
AU  - Shangling Jui
AU  - Joost Van de Weijer
A2  - BMVC
PY  - 2022//
TI  - Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification
BT  - 33rd British Machine Vision Conference
N2  - Lifelong object re-identification incrementally learns from a stream of re-identification tasks. The objective is to learn a representation that can be applied to all tasks and that generalizes to previously unseen re-identification tasks. The main challenge is that at inference time the representation must generalize to previously unseen identities. To address this problem, we apply continual meta metric learning to lifelong object re-identification. To prevent forgetting of previous tasks, we use knowledge distillation and explore the roles of positive and negative pairs. Based on our observation that the distillation and metric losses are antagonistic, we propose to remove positive pairs from distillation to robustify model updates. Our method, called Distillation without Positive Pairs (DwoPP), is evaluated on extensive intra-domain experiments on person and vehicle re-identification datasets, as well as inter-domain experiments on the LReID benchmark. Our experiments demonstrate that DwoPP significantly outperforms the state-of-the-art.
N1  - LAMP; 600.147
ID  - Kai Wang2022
ER  -