arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.14574cs.ROcs.CV
收藏

一点注意力是所有你需要的人重新识别

A Little Bit Attention Is All You Need for Person Re-Identification

TU Ilmenau(伊尔默瑙工业大学)

Markus Eisenbach, Jannik Lübberstedt, Dustin Aganian, Horst-Michael Gross

摘要:

人员重新识别在移动机器人需要长时间跟踪其用户的应用中起着关键作用,即使他们在一段时间内部分未被观察到,以便跟随他们或按需提供。在这种情况下,移动机器人上基于深度学习的实时特征提取通常在专用设备上执行,这些专用设备的计算资源为多个任务共享。因此,必须考虑推理速度。相比之下,人的重新识别往往是通过架构的变化来改善的,这是以显著减慢推理为代价的。注意力障碍就是这样一个例子。我们将证明,一些性能良好的注意力块中使用的最先进的推理成本太高,以证明他们的使用移动机器人应用程序。因此,我们提出了一个注意力块,它只会轻微影响推理速度,同时在重新识别准确性方面跟上更深的网络或更复杂的注意力块。我们进行广泛的神经架构搜索,以获得规则,在该位置的注意力块应该被集成到架构中,以实现速度和准确性之间的最佳权衡。最后,我们确认,在重新识别基准上的最佳性能配置在室内机器人数据集上也表现良好。

英文摘要:

Person re-identification plays a key role in applications where a mobile robot needs to track its users over a long period of time, even if they are partially unobserved for some time, in order to follow them or be available on demand. In this context, deep-learning based real-time feature extraction on a mobile robot is often performed on special-purpose devices whose computational resources are shared for multiple tasks. Therefore, the inference speed has to be taken into account. In contrast, person re-identification is often improved by architectural changes that come at the cost of significantly slowing down inference. Attention blocks are one such example. We will show that some well-performing attention blocks used in the state of the art are subject to inference costs that are far too high to justify their use for mobile robotic applications. As a consequence, we propose an attention block that only slightly affects the inference speed while keeping up with much deeper networks or more complex attention blocks in terms of re-identification accuracy. We perform extensive neural architecture search to derive rules at which locations this attention block should be integrated into the architecture in order to achieve the best trade-off between speed and accuracy. Finally, we confirm that the best performing configuration on a re-identification benchmark also performs well on an indoor robotic dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑