AiATrack: Attention in Attention for Transformer Visual Tracking
This work addresses a specific bottleneck in visual tracking for applications like surveillance or robotics, representing an incremental improvement over existing Transformer trackers.
The paper tackled the problem of noisy attention weights in Transformer visual trackers by proposing an attention in attention (AiA) module to enhance correlations and suppress errors, achieving state-of-the-art performance on six benchmarks with real-time speed.
Transformer trackers have achieved impressive advancements recently, where the attention mechanism plays an important role. However, the independent correlation computation in the attention mechanism could result in noisy and ambiguous attention weights, which inhibits further performance improvement. To address this issue, we propose an attention in attention (AiA) module, which enhances appropriate correlations and suppresses erroneous ones by seeking consensus among all correlation vectors. Our AiA module can be readily applied to both self-attention blocks and cross-attention blocks to facilitate feature aggregation and information propagation for visual tracking. Moreover, we propose a streamlined Transformer tracking framework, dubbed AiATrack, by introducing efficient feature reuse and target-background embeddings to make full use of temporal references. Experiments show that our tracker achieves state-of-the-art performance on six tracking benchmarks while running at a real-time speed.