Double Branch Attention Block for Discriminative Representation of Siamese Trackers

Abstract

Siamese trackers have achieved a good balance between accuracy and efficiency in generic object tracking. However, background distractors cause side effects to the discriminative representation of the target. To suppress the sensitivity of trackers to background distractors, we propose a Double Branch Attention (DBA) block and a Siamese tracker equipped with the DBA block named DBA-Siam. First, the DBA block concatenates channels of multiple layers from two branches of the Siamese framework to obtain rich feature representation. Second, the channel attention is applied to the two concatenated feature blocks to enhance the robust features selectively, thus enhancing the ability to distinguish the target from the complex background. Finally, the DBA block collects the contextual relevance between the Siamese branches and adaptively encodes it into the feature weight of the detection branch for information compensation. Ablation experiments show that the proposed block can enhance the discriminative representation of the target and significantly improve the tracking performance. Results on two popular benchmarks show that DBA-Siam performs favorably against its counterparts. Compared with the advanced algorithm CSTNet, DBA-Siam improves the EAO by 18.9% on VOT2016.

Visual Tracking with FPN Based on Transformer and Response Map Enhancement

“…Based on SiamFC, SiamRPN adopts anchors for region proposal to make use of the deep feature maps and avoid repeated computation, which has great speed performance. Subsequent studies have improved SiamRPN from the aspects of feature extraction, proportion of positive and negative samples, feature enhancement and so on [15,16]. However, the anchor-based trackers are very sensitive to relative hyper-parameters such as size, number and aspect ratio of anchor boxes.…”