AMTT: An End-to-End Anchor-Based Multi-Scale Transformer Tracking Method

Abstract

Most current trackers utilize only the highest-level features to achieve faster tracking performance, making it difficult to achieve accurate tracking of small and low-resolution objects. To address this problem, we propose an end-to-end anchor-based multi-scale transformer tracking (AMTT) approach to improve the tracking performance of the network for objects of different sizes. First, we design a multi-scale feature encoder based on the deformable transformer, which better fuses the multilayer template features and search features through the self-enhancement module and cross-enhancement module to improve the attention of the whole network to objects of different sizes. Then, to reduce the computational overhead of the decoder while further enhancing the multi-scale features, we design a feature focusing block to compress the number of coded features. Finally, we introduce a feature anchor into the traditional decoder and design an anchor-based decoder, which utilizes the feature anchor to guide the decoder to adapt to changes in object scale and achieve more accurate tracking performance. To confirm the effectiveness of our proposed method, we conduct a series of experiments on different datasets such as UAV123, OTB100 and GOT10k. The results show that our adopted method exhibits highly competitive performance compared to the state-of-the-art methods in recent years.