Abstract:
One-stream Transformer-based trackers have demonstrated remarkable performance
by concatenating template and search region tokens, thereby enabling
joint attention across all tokens. However, enabling a large number
of background search tokens to attend to the target template tokens weakens
the tracker’s discriminative capability. Several token pruning methods
have been proposed to mitigate background interference; however, they often
remove tokens near the target, leading to the loss of essential contextual
information and degraded tracking performance. Moreover, the presence of
distractors within the search tokens further reduces the tracker’s ability to
accurately identify the target. To address these limitations, we propose CPDATrack,
a novel tracking framework designed to suppress interference from
background and distractor tokens while enhancing computational efficiency.
First, a learnable module is integrated between two designated encoder layers
to estimate the probability of each search token being associated with the target.
Based on these estimates, less-informative background tokens are pruned
from the search region while preserving the contextual cues surrounding the
target. To further suppress background interference, a discriminative selective
attention mechanism is employed that fully blocks search-to-template attention
in the early layers. In the subsequent encoder layers, high-probability target tokens are selectively extracted from a localized region to attend to the
template tokens, thereby reducing the influence of background and distractor
tokens. The proposed CPDATrack achieves state-of-the-art performance on
multiple benchmarks, particularly excelling in one-shot tracking on GOT-10k
with an average overlap of 75.1%. The code, models, and results of this work
are available at https://github.com/JananiKugaa/CPDATrack.git.
