论文标题
GSCONV的Slim-Neck：实时检测器体系结构的轻巧设计
Slim-neck by GSConv: A lightweight-design for real-time detector architectures
论文作者
论文摘要
实时对象检测对于工业和研究领域很重要。在边缘设备上，很难实现实时检测要求，并且由大量深度可分离卷积建立的轻量级模型无法达到足够的准确性。我们引入了一种新的轻量级卷积技术GSCONV，以减轻模型，但要保持准确性。 GSCONV在准确性和速度之间取得了良好的权衡。此外，我们提供了基于GSCONV，SLIM-NECK（SNS）的设计建议，以实现实时检测器的较高计算成本效益。 SNS的有效性在二十多组比较实验中得到了强大的证明。特别是，与基准相比，SNS改善的实时检测器得到了最新的（在Tesla T4上以〜100fps的速度）获得最新的AP50。代码可从https://github.com/alanli1997/slim-neck-by-gsconv获得。
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 ~ 100FPS on a Tesla T4) compared with the baselines. Code is available at https://github.com/alanli1997/slim-neck-by-gsconv
