DeforT: Deformable transformer for visual tracking.

ABSTRACT

Most trackers formulate visual tracking as common classification and regression (i.e., bounding box regression) tasks. Correlation features that are computed through depth-wise convolution or channel-wise multiplication operations are input into both the classification and regression branches for inference. However, this matching computation with the linear correlation method tends to lose semantic features and obtain only a local optimum. Moreover, these trackers use an unreliable ranking based on the classification score and the intersection over union (IoU) loss for the regression training, thus degrading the tracking performance. In this paper, we introduce a deformable transformer model, which effectively computes the correlation features of the training and search sets. A new loss called the quality-aware focal loss (QAFL) is used to train the classification network; it efficiently alleviates the inconsistency between the classification and localization quality predictions. We use a new regression loss called α-GIoU to train the regression network, and it effectively improves localization accuracy. To further improve the tracker's robustness, the candidate object location is predicted by using a combination of online learning scores with a transformer-assisted framework and classification scores. An extensive experiment on six testing datasets demonstrates the effectiveness of our method. In particular, the proposed method attains a success score of 71.7% on the OTB-2015 dataset and an AUC score of 67.3% on the NFS30 dataset, respectively.