Unsupervised Cross-Modal Distillation for Thermal Infrared Tracking
Jingxian Sun, Lichao Zhang, Yufei Zha, Abel González-García, Peng Zhang, Wei Huang, Yanning Zhang · 2021
The target representation learned by convolutional neural networks plays an important role in Thermal Infrared (TIR) tracking. Currently, most of the top-performing TIR trackers are still employing representations learned by the model trained on the RGB data. However, this representation does not take into account the information in the TIR modality itself, limiting the performance of TIR tracking.