Robust Visual Object Tracking via Adaptive Attribute-Aware Discriminative Correlation Filters

In recent years, attention mechanisms have been widely studied in Discriminative Correlation Filter (DCF) based visual object tracking. To realise spatial attention and discriminative features mining, existing approaches usually apply regularisation terms to the spatial dimension of multi-channel features. However, these spatial regularisation approaches construct a shared spatial attention pattern for the entire multi-channel features, without considering the diversity across channels. As each feature map (channel) focuses on a specific visual attribute, a shared spatial attention pattern limits the capability for mining important information from different channels. To address this issue, we advocate channel-specific spatial attention for DCF-based trackers. The key ingredient of the proposed method is an Adaptive Attribute-Aware spatial attention mechanism for constructing a novel DCF-based tracker (A3DCF). To highlight the discriminative elements in each feature map, spatial sparsity is imposed in the filter learning stage, moderated by the prior knowledge regarding the expected concentration of signal energy. In addition, we perform a post processing of the identified spatial patterns to alleviate the impact of less significant channels. The net effect is that the irrelevant and inconsistent channels are removed by the proposed method. The results obtained on well-known benchmarks, e.g., OTB2015, DTB70, UAV123, VOT2018, LaSOT, GOT10K and TrackingNet, demonstrate the merits of our A3DCF method, with improve.g.ed performance against the state-of-the-art methods.