Person Re-IDentification Based on Mutual Learning With Embedded Noise Block

Abstract

Some person re-identification(Re-ID) algorithms based on deep learning utilizes a baseline as basis to modify, and add some strategies to achieve better performance. Different from the conventional methods, this work combines distillation with mutual learning to construct a person Re-ID model of mutual learning. In training, in view of the characteristics of metric learning, we introduce a mutual loss $L_{M2}$ in the mutual learning network, so as to better promote the student networks to mine complementary information. In order to overcome the coupling problem in mutual learning, we designed a lightweight noise block and embedded it into mutual learning, which greatly improves the complementarity between networks. It should be added that the improvement achieved on the poor baseline can’t strictly prove the effectiveness of the research, so this paper constructs a person Re-ID baseline with relatively good performance, which is used as the student networks in mutual learning. Experiments demonstrate that the proposed person Re-ID algorithm based on mutual learning with embedded noise block achieves competitive performance on the Market1501, DukeMTMC-ReID, and CUHK-03 datasets.

Keywords

• Person re-identification
• mutual learning
• knowledge distillation
• network decoupling