论文标题
如何在任何数据集上训练准确有效的对象检测模型
How to Train an Accurate and Efficient Object Detection Model on Any Dataset
论文作者
论文摘要
快速发展的行业需要模型的高精度，而无需进行微调所需的耗时和计算昂贵的实验。此外，曾经针对特定数据集进行了仔细优化的模型和培训管道，很少能很好地推广到其他数据集上的培训。这使得为每种用例都精心调整模型是不现实的。为了解决这个问题，我们提出了一种替代方法，该方法还构成了Intel Geti平台的骨干：用于对象检测培训的数据集 - 无形模板，该模板由精心选择和预先训练的模型以及强大的培训管道以及用于进一步培训的强大培训管道组成。我们的解决方案在开箱即用，并在广泛的数据集上提供了强大的基线。它可以单独使用，也可以用作需要在需要时进行特定用例进行微调的起点。我们通过在数据集的语料库上进行并行培训，并优化整个语料库中的平均结果，从而优化了架构和培训技巧的选择，从而获得了数据集 - 不足的模板。考虑到绩效准确的权衡，我们检查了许多架构。因此，我们建议使用OpenVino Toolkit在CPU上部署3名决赛选手VFNET，ATSS和SSD。源代码可作为OpenVino培训扩展的一部分（https://github.com/openvinotoolkit/training_extensions}
The rapidly evolving industry demands high accuracy of the models without the need for time-consuming and computationally expensive experiments required for fine-tuning. Moreover, a model and training pipeline, which was once carefully optimized for a specific dataset, rarely generalizes well to training on a different dataset. This makes it unrealistic to have carefully fine-tuned models for each use case. To solve this, we propose an alternative approach that also forms a backbone of Intel Geti platform: a dataset-agnostic template for object detection trainings, consisting of carefully chosen and pre-trained models together with a robust training pipeline for further training. Our solution works out-of-the-box and provides a strong baseline on a wide range of datasets. It can be used on its own or as a starting point for further fine-tuning for specific use cases when needed. We obtained dataset-agnostic templates by performing parallel training on a corpus of datasets and optimizing the choice of architectures and training tricks with respect to the average results on the whole corpora. We examined a number of architectures, taking into account the performance-accuracy trade-off. Consequently, we propose 3 finalists, VFNet, ATSS, and SSD, that can be deployed on CPU using the OpenVINO toolkit. The source code is available as a part of the OpenVINO Training Extensions (https://github.com/openvinotoolkit/training_extensions}
