Bi-level deep mutual learning assisted multi-task network for occluded person re-identification

An occluded person re-identification (ReID) approach is presented by constructing a Bi-level deep Mutual learning assisted Multi-task network (BMM), where the holistic and occluded person ReID tasks are treated as two related but not identical tasks. This is inspired by the human perception characteristic that there exist both similarities and differences when human views a holistic image and the occluded one. Specifically, a multi-task network with two branches is designed, where the convolutional neural network based feature representation part shares the weights by two tasks for commonality extraction, while the following output layers have respective weights for difference representation. Furthermore, as the non-occluded regions convey discriminative information, a bi-level mutual learning strategy is proposed and applied mutually on two branches to obtain more effective information from the non-occluded regions in the occluded images for better identity recognition. This is achieved by both feature-level and output-level mutual loss functions. Extensive experiments prove the advantages of the BMM for person ReID.

Automated summary

This paper presents an occluded person re-identification approach by constructing a bi-level deep mutual learning assisted multi-task network. The network treats holistic and occluded person ReID tasks as related but not identical tasks and employs a multi-task network with two branches. A mutual learning strategy is proposed and applied on both branches to extract more effective information for better identity recognition. Extensive experiments demonstrate the advantages of this approach for person ReID.