Real-time object detection is significant for industrial and research fields. On edge devices, a giant model is difficult to achieve the real-time detecting requirement, and a lightweight model built from a large number of the depth-wise separable convolutional could not achieve the sufficient accuracy. We introduce a new lightweight convolutional technique, GSConv, to lighten the model but maintain the accuracy. The GSConv accomplishes an excellent trade-off between the accuracy and speed. Furthermore, we provide a design suggestion based on the GSConv, slim-neck (SNs), to achieve a higher computational cost-effectiveness of the real-time detectors. The effectiveness of the SNs was robustly demonstrated in over twenty sets comparative experiments. In particular, the real-time detectors of ameliorated by the SNs obtain the state-of-the-art (70.9% AP₅₀ for the SODA10M at a speed of ~ 100 FPS on a Tesla T4) compared with the baselines. Code is available at https://github.com/alanli1997/slim-neck-by-gsconv.

实时目标检测对于工业和研究领域具有重要意义。在边缘设备上，巨大的模型很难达到实时检测的要求，而由大量深度可分离卷积构建的轻量级模型也无法达到足够的精度。我们引入了一种新的轻量级卷积技术 GSConv，以减轻模型重量但保持准确性。 GSConv 在精度和速度之间实现了出色的平衡。此外，我们提供了基于 GSConv、细颈（SN）的设计建议，以实现实时检测器更高的计算成本效益。 SN 的有效性在二十多组对比实验中得到了有力证明。特别是，与基线相比，通过 SN 改进的实时检测器获得了最先进的性能（SODA10M 在 Tesla T4 上以约 100 FPS 的速度获得了 70.9% AP ₅₀ ）。代码可在 https://github.com/alanli1997/slim-neck-by-gsconv 获取。