论文标题
早期出口语义细分网络中的基于类的阈值
Class Based Thresholding in Early Exit Semantic Segmentation Networks
论文作者
论文摘要
我们建议基于类的阈值（CBT），以降低早期出口语义分割模型的计算成本，同时保持平均值与联合性能（MIOU）性能。 CBT的一个关键思想是利用自然存在的神经崩溃现象。具体而言，通过计算训练集中每个类的平均预测概率，CBT可以为每个类分配不同的屏蔽阈值值，以便可以对易于预测类的像素更快地终止计算。我们显示了CBT对CityScapes和ADE20K数据集的有效性。与先前最先进的早期出口模型相比，CBT可以将计算成本降低$ 23 \％$。
We propose Class Based Thresholding (CBT) to reduce the computational cost of early exit semantic segmentation models while preserving the mean intersection over union (mIoU) performance. A key idea of CBT is to exploit the naturally-occurring neural collapse phenomenon. Specifically, by calculating the mean prediction probabilities of each class in the training set, CBT assigns different masking threshold values to each class, so that the computation can be terminated sooner for pixels belonging to easy-to-predict classes. We show the effectiveness of CBT on Cityscapes and ADE20K datasets. CBT can reduce the computational cost by $23\%$ compared to the previous state-of-the-art early exit models.
