论文标题
标签：一种新的中间监督方法用于对象检测
LabelEnc: A New Intermediate Supervision Method for Object Detection
论文作者
论文摘要
在本文中，我们提出了一种名为Labelenc的新的中间监督方法，以增强对象检测系统的训练。关键思想是引入一种新颖的标签编码功能，将地面真相标签映射到潜在的嵌入中，并在训练过程中充当检测主链的辅助中间监督。我们的方法主要涉及两步培训程序。首先，我们通过标签空间中定义的自动编码器优化标签编码函数，近似目标对象检测器的“所需”中间表示。其次，利用学到的标签编码功能，我们引入了检测骨架附加的新辅助损失，从而使派生的检测器的性能受益。实验表明，无论一级或两个阶段的框架，我们的方法在可可数据集上都将各种检测系统提高了约2％。此外，辅助结构仅在训练过程中存在，即在推理时间完全没有成本。代码可在以下网址找到：https：//github.com/megvii-model/labelenc
In this paper we propose a new intermediate supervision method, named LabelEnc, to boost the training of object detection systems. The key idea is to introduce a novel label encoding function, mapping the ground-truth labels into latent embedding, acting as an auxiliary intermediate supervision to the detection backbone during training. Our approach mainly involves a two-step training procedure. First, we optimize the label encoding function via an AutoEncoder defined in the label space, approximating the "desired" intermediate representations for the target object detector. Second, taking advantage of the learned label encoding function, we introduce a new auxiliary loss attached to the detection backbones, thus benefiting the performance of the derived detector. Experiments show our method improves a variety of detection systems by around 2% on COCO dataset, no matter one-stage or two-stage frameworks. Moreover, the auxiliary structures only exist during training, i.e. it is completely cost-free in inference time. Code is available at: https://github.com/megvii-model/LabelEnc
