ReMaX：放松以获得更好的高效全景分割训练

ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation

June 29, 2023

作者: Shuyang Sun, Weijun Wang, Qihang Yu, Andrew Howard, Philip Torr, Liang-Chieh Chen

cs.AI

摘要

本文提出了一种新机制，用于促进面向全景分割的口罩变换器的训练，使其部署更加普及化。我们观察到，由于其高复杂性，全景分割的训练目标将不可避免地导致更高的假阳性惩罚。这种不平衡的损失使得基于端到端口罩变换器的架构的训练过程变得困难，特别是对于高效模型。在本文中，我们提出了ReMaX，它在面向全景分割的训练过程中为口罩预测和类别预测添加了放松。我们展示了通过这些简单的放松技术，在训练过程中，我们的模型可以在不增加任何额外计算成本的情况下，始终得到明显的改进。通过将我们的方法与MobileNetV3-Small等高效骨干网络结合使用，我们的方法在COCO、ADE20K和Cityscapes上实现了高效全景分割的新的最先进结果。代码和预训练检查点将在https://github.com/google-research/deeplab2 上提供。

English

This paper presents a new mechanism to facilitate the training of mask transformers for efficient panoptic segmentation, democratizing its deployment. We observe that due to its high complexity, the training objective of panoptic segmentation will inevitably lead to much higher false positive penalization. Such unbalanced loss makes the training process of the end-to-end mask-transformer based architectures difficult, especially for efficient models. In this paper, we present ReMaX that adds relaxation to mask predictions and class predictions during training for panoptic segmentation. We demonstrate that via these simple relaxation techniques during training, our model can be consistently improved by a clear margin without any extra computational cost on inference. By combining our method with efficient backbones like MobileNetV3-Small, our method achieves new state-of-the-art results for efficient panoptic segmentation on COCO, ADE20K and Cityscapes. Code and pre-trained checkpoints will be available at https://github.com/google-research/deeplab2.