GiraffeDet:一种用于目标检测的重颈模型
GiraffeDet: A Heavy-Neck Paradigm for Object Detection
摘要:
在传统的目标检测框架中,从图像识别模型继承的骨干主体提取深层潜在特征,然后颈部模块融合这些潜在特征以捕获不同尺度的信息。由于目标检测中的分辨率比图像识别中的分辨率大得多,因此主干的计算成本通常主导总推理成本。这种重型骨干设计范例主要是由于将图像识别模型转移到目标检测时的历史遗留问题,而不是用于目标检测的端到端优化设计。在这项工作中,我们表明,这种模式确实导致次优的目标检测模型。为此,我们提出了一种新的重颈范例,GiraffeDet,一个长颈鹿般的网络,有效的目标检测。GiraffeDet使用一个非常轻量级的骨干和一个非常深和大的颈部模块,鼓励密集的信息交换之间的不同空间尺度以及不同层次的潜在语义同时。这种设计范式允许检测器在网络的早期阶段以相同的优先级处理高层语义信息和低层空间信息,使其在检测任务中更有效。多个流行的目标检测基准的数值评估表明,GiraffeDet始终优于以前的SOTA模型在广泛的资源限制。源代码可在https://github.com/jyqi/GiraffeDet上获得。
英文摘要:
In conventional object detection frameworks, a backbone body inherited from image recognition models extracts deep latent features and then a neck module fuses these latent features to capture information at different scales. As the resolution in object detection is much larger than in image recognition, the computational cost of the backbone often dominates the total inference cost. This heavy-backbone design paradigm is mostly due to the historical legacy when transferring image recognition models to object detection rather than an end-to-end optimized design for object detection. In this work, we show that such paradigm indeed leads to sub-optimal object detection models. To this end, we propose a novel heavy-neck paradigm, GiraffeDet, a giraffe-like network for efficient object detection. The GiraffeDet uses an extremely lightweight backbone and a very deep and large neck module which encourages dense information exchange among different spatial scales as well as different levels of latent semantics simultaneously. This design paradigm allows detectors to process the high-level semantic information and low-level spatial information at the same priority even in the early stage of the network, making it more effective in detection tasks. Numerical evaluations on multiple popular object detection benchmarks show that GiraffeDet consistently outperforms previous SOTA models across a wide spectrum of resource constraints. The source code is available at https://github.com/jyqi/GiraffeDet.
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。