Foreground-Background Distribution Modeling Transformer for Visual Object Tracking

Dawei Yang, Jianfeng He, Yinchao Ma, Qianjin Yu, Tianzhu Zhang; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 10117-10127


Visual object tracking is a fundamental research topic with a broad range of applications. Benefiting from the rapid development of Transformer, pure Transformer trackers have achieved great progress. However, the feature learning of these Transformer-based trackers is easily disturbed by complex backgrounds. To address the above limitations, we propose a novel foreground-background distribution modeling transformer for visual object tracking (F-BDMTrack), including a fore-background agent learning (FBAL) module and a distribution-aware attention (DA2) module in a unified transformer architecture. The proposed F-BDMTrack enjoys several merits. First, the proposed FBAL module can effectively mine fore-background information with designed fore-background agents. Second, the DA2 module can suppress the incorrect interaction between foreground and background by modeling fore-background distribution similarities. Finally, F-BDMTrack can extract discriminative features under ever-changing tracking scenarios for more accurate target state estimation. Extensive experiments show that our F-BDMTrack outperforms previous state-of-the-art trackers on eight tracking benchmarks.

Related Material

[pdf] [supp]
@InProceedings{Yang_2023_ICCV, author = {Yang, Dawei and He, Jianfeng and Ma, Yinchao and Yu, Qianjin and Zhang, Tianzhu}, title = {Foreground-Background Distribution Modeling Transformer for Visual Object Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10117-10127} }