CREST: Convolutional Residual Learning for Visual Tracking
This work addresses visual tracking for computer vision applications, offering an incremental improvement by integrating end-to-end learning into DCF-based methods.
The paper tackled the problem of discriminative correlation filters (DCFs) in visual tracking, which suffer from separate training and non-end-to-end updates, by proposing CREST, a method that reformulates DCFs as a convolutional neural network with residual learning for end-to-end training, resulting in favorable performance against state-of-the-art trackers on benchmark datasets.
Discriminative correlation filters (DCFs) have been shown to perform superiorly in visual tracking. They only need a small set of training samples from the initial frame to generate an appearance model. However, existing DCFs learn the filters separately from feature extraction, and update these filters using a moving average operation with an empirical weight. These DCF trackers hardly benefit from the end-to-end training. In this paper, we propose the CREST algorithm to reformulate DCFs as a one-layer convolutional neural network. Our method integrates feature extraction, response map generation as well as model update into the neural networks for an end-to-end training. To reduce model degradation during online update, we apply residual learning to take appearance changes into account. Extensive experiments on the benchmark datasets demonstrate that our CREST tracker performs favorably against state-of-the-art trackers.