Recognizing a target of interest from the UAVs is much more challenging than
the existing object re-identification tasks across multiple city cameras. The
images taken by the UAVs usually suffer from significant size difference when
generating the object bounding boxes and uncertain rotation variations.
Existing methods are usually designed for city cameras, incapable of handing
the rotation issue in UAV scenarios. A straightforward solution is to perform
the image-level rotation augmentation, but it would cause loss of useful
information when inputting the powerful vision transformer as patches. This
motivates us to simulate the rotation operation at the patch feature level,
proposing a novel rotation invariant vision transformer (RotTrans). This
strategy builds on high-level features with the help of the specificity of the
vision transformer structure, which enhances the robustness against large
rotation differences. In addition, we design invariance constraint to establish
the relationship between the original feature and the rotated features,
achieving stronger rotation invariance. Our proposed transformer tested on the
latest UAV datasets greatly outperforms the current state-of-the-arts, which is
5.9\% and 4.8\% higher than the highest mAP and Rank1. Notably, our model also
performs competitively for the person re-identification task on traditional
city cameras. In particular, our solution wins the first place in the UAV-based
person re-recognition track in the Multi-Modal Video Reasoning and Analyzing
Competition held in ICCV 2021. Code is available at
this https URL

我们提出了一种新颖的旋转不变视觉变形器（RotTrans），利用视觉变形器的结构特点，在高级特征的基础上建立不变度约束，以增强模型对大旋转差异的鲁棒性。在最新的 UAV 数据集上，我们的模型表现优于现有的最先进技术，其 mAP 和 Rank1 值分别比最高值提高了 5.9% 和 4.8%。值得注意的是，我们的模型在传统城市摄像头上的人物再识别任务中也取得了竞争优势，在 ICCV 2021 年举办的多模式视频推理与分析比赛的基于 UAV 的人物重新识别赛道上获得第一名。