Learn from restoration: exploiting task-oriented knowledge distillation in self-supervised person re-identification

Person re-identification (ReID) aims to identify such individuals across diverse surveillance scenarios, which plays a pivotal role in centralized monitoring. However, very recent studies pre-trained their models on ImageNet and fine-tuned on specific downstream ReID dataset, which leads to restricted generalization capability on identifying person images in poor imaging conditions. In order to address such limitation, this paper introduces a Self-Supervised Learning model with Task-Oriented Knowledge Distillation for person ReID. The ReID-oriented Prior is proposed to simulate the primary challenges of low-quality imaging and occlusion in real-world scenarios, while the teacher–student network along with relative projectors is adopted as the knowledge distillation paradigm. By incorporating multiple loss functions, the self-supervised network aims not only to restore detailed and masked embeddings but also to align invariant representations between partial and complete semantics. Our model is pre-trained on a person-specific dataset LUPerson without additional head-craft labels. Extensive experiments carried out on Market1501, MSMT17, and Occluded-Duke show that our method yields the state-of-the-art performance on supervised person ReID. Moreover, the proposed method could obtain the remarkable performance on partial and unsupervised person ReID, which further indicates the strong generalizability of our method. The code is publicly available at https://github.com/ICT-CVlab/Oriented-KD-SSL .