Dense Feature Aggregation and Pruning for RGBT Tracking
This work addresses the core challenge of modality fusion in RGBT tracking, offering an incremental improvement over existing methods.
The paper tackled the problem of effective information fusion for RGBT tracking by proposing a deep fusion algorithm that densely aggregates and collaboratively prunes features from different modalities, achieving state-of-the-art performance on two benchmark datasets.
How to perform effective information fusion of different modalities is a core factor in boosting the performance of RGBT tracking. This paper presents a novel deep fusion algorithm based on the representations from an end-to-end trained convolutional neural network. To deploy the complementarity of features of all layers, we propose a recursive strategy to densely aggregate these features that yield robust representations of target objects in each modality. In different modalities, we propose to prune the densely aggregated features of all modalities in a collaborative way. In a specific, we employ the operations of global average pooling and weighted random selection to perform channel scoring and selection, which could remove redundant and noisy features to achieve more robust feature representation. Experimental results on two RGBT tracking benchmark datasets suggest that our tracker achieves clear state-of-the-art against other RGB and RGBT tracking methods.