Self-supervised discriminative model prediction for visual tracking

The discriminative model prediction (DiMP) object tracking model is an excellent end-to-end tracking framework and have achieved the best results of its time. However, there are two problems with DiMP in the process of actual use: (1) DiMP is prone to interference from similar objects during the tracking process, and (2) DiMP requires a large amount of labeled data for training. In this paper, we propose two methods to enhance the robustness of interference to similar objects in target tracking: multi-scale region search and Gaussian convolution-based response map processing. Simultaneously, aiming at tackling the issue of requiring a large amount of labeled data for training, we implement self-supervised training based on forward-backward tracking for the DiMP tracking method. Furthermore, a new consistency loss function is designed to better self-supervised training. Extensive experiments show that the enhancements implemented in the DiMP tracking framework can bolster its robustness, and the tracker based on self-supervised training has outstanding tracking performance.