将区域随机化应用于合成数据的目标类别检测
Applying Domain Randomization to Synthetic Data for Object Category Detection
摘要:
基于深度学习的目标检测技术的最新进展已经彻底改变了它们在若干领域中的适用性。然而,由于这些方法依赖于庞大且大量的数据,因此通常的做法是下载在标准数据集上预先训练的模型,并使用一小组领域相关图像对特定应用领域进行微调。在这项工作中,我们证明了使用不一定具有照片真实感的合成数据集可以成为简单微调预训练网络的更好替代方案。具体来说,我们的结果显示了一个令人印象深刻的25%的改进mAP指标超过微调基线时,只有约200个标记的图像可用于训练。最后,我们的研究结果的消融研究,描绘在随机化管道中的不同组件的个人贡献。
英文摘要:
Recent advances in deep learning-based object detection techniques have revolutionized their applicability in several fields. However, since these methods rely on unwieldy and large amounts of data, a common practice is to download models pre-trained on standard datasets and fine-tune them for specific application domains with a small set of domain relevant images. In this work, we show that using synthetic datasets that are not necessarily photo-realistic can be a better alternative to simply fine-tune pre-trained networks. Specifically, our results show an impressive 25% improvement in the mAP metric over a fine-tuning baseline when only about 200 labelled images are available to train. Finally, an ablation study of our results is presented to delineate the individual contribution of different components in the randomization pipeline.
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。