论文标题
实时语义分割的基于熵的特征提取
Entropy-Based Feature Extraction For Real-Time Semantic Segmentation
论文作者
论文摘要
本文介绍了一个有效的基于补丁的计算模块，基于熵的补丁编码器（EPE）模块，用于资源受限的语义分割。 EPE模块由三个轻巧的全趋验编码器组成，每个编码器都会从具有不同熵的图像贴片中提取特征。具有最大参数数量的编码器正在处理具有高熵的补丁，带有中等数量参数的编码器处理了中等熵的贴片，并且最小的编码器处理了低熵的贴片。模块背后的直觉是：由于具有较高熵的补丁包含更多信息，因此它们需要具有更多参数的编码器，与低熵补丁不同，可以使用小编码器处理。因此，通过较小的编码器处理部分可以显着降低模块的计算成本。实验表明，EPE可以提高现有的实时语义分割模型的性能，而计算成本却略有增加。具体而言，EPE将DFANET A的MIOU性能提高了0.9％，而参数数量仅增加1.2％，而MIOU的性能则增加了1％，而模型参数增加了10％。
This paper introduces an efficient patch-based computational module, coined Entropy-based Patch Encoder (EPE) module, for resource-constrained semantic segmentation. The EPE module consists of three lightweight fully-convolutional encoders, each extracting features from image patches with a different amount of entropy. Patches with high entropy are being processed by the encoder with the largest number of parameters, patches with moderate entropy are processed by the encoder with a moderate number of parameters, and patches with low entropy are processed by the smallest encoder. The intuition behind the module is the following: as patches with high entropy contain more information, they need an encoder with more parameters, unlike low entropy patches, which can be processed using a small encoder. Consequently, processing part of the patches via the smaller encoder can significantly reduce the computational cost of the module. Experiments show that EPE can boost the performance of existing real-time semantic segmentation models with a slight increase in the computational cost. Specifically, EPE increases the mIOU performance of DFANet A by 0.9% with only 1.2% increase in the number of parameters and the mIOU performance of EDANet by 1% with 10% increase of the model parameters.
