Deep Attentive Tracking via Reciprocative Learning
This work addresses visual tracking problems for computer vision applications, offering an incremental improvement by integrating attention mechanisms into existing tracking-by-detection frameworks.
The paper tackles the challenge of tracking objects with large appearance changes by proposing a reciprocative learning algorithm that uses attention maps as regularization to train deep classifiers, achieving favorable performance against state-of-the-art methods on large-scale benchmarks.
Visual attention, derived from cognitive neuroscience, facilitates human perception on the most pertinent subset of the sensory data. Recently, significant efforts have been made to exploit attention schemes to advance computer vision systems. For visual tracking, it is often challenging to track target objects undergoing large appearance changes. Attention maps facilitate visual tracking by selectively paying attention to temporal robust features. Existing tracking-by-detection approaches mainly use additional attention modules to generate feature weights as the classifiers are not equipped with such mechanisms. In this paper, we propose a reciprocative learning algorithm to exploit visual attention for training deep classifiers. The proposed algorithm consists of feed-forward and backward operations to generate attention maps, which serve as regularization terms coupled with the original classification loss function for training. The deep classifier learns to attend to the regions of target objects robust to appearance changes. Extensive experiments on large-scale benchmark datasets show that the proposed attentive tracking method performs favorably against the state-of-the-art approaches.