Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation
This addresses the problem of accurate object tracking and segmentation in videos for computer vision applications, representing an incremental advance over existing methods.
The paper tackles multiple object tracking and segmentation by proposing Prototypical Cross-Attention Network (PCAN), which leverages spatio-temporal information to improve performance, achieving state-of-the-art results on Youtube-VIS and BDD100K datasets.
Multiple object tracking and segmentation requires detecting, tracking, and segmenting objects belonging to a set of given classes. Most approaches only exploit the temporal dimension to address the association problem, while relying on single frame predictions for the segmentation mask itself. We propose Prototypical Cross-Attention Network (PCAN), capable of leveraging rich spatio-temporal information for online multiple object tracking and segmentation. PCAN first distills a space-time memory into a set of prototypes and then employs cross-attention to retrieve rich information from the past frames. To segment each object, PCAN adopts a prototypical appearance module to learn a set of contrastive foreground and background prototypes, which are then propagated over time. Extensive experiments demonstrate that PCAN outperforms current video instance tracking and segmentation competition winners on both Youtube-VIS and BDD100K datasets, and shows efficacy to both one-stage and two-stage segmentation frameworks. Code and video resources are available at http://vis.xyz/pub/pcan.