The recent development of light-weighted neural networks has promoted the applications of deep learning under resource constraints and mobile applications. Many of these applications need to perform a real-time and efficient prediction for semantic segmentation with a light-weighted network. This paper introduces a light-weighted network with an efficient reduced non-local module (LRNNet) for efficient and realtime semantic segmentation. We proposed a factorized convolutional block in ResNet-Style encoder to achieve more lightweighted, efficient and powerful feature extraction. Meanwhile, our proposed reduced non-local module utilizes spatial regional dominant singular vectors to achieve reduced and more representative non-local feature integration with much lower computation and memory cost. Experiments demonstrate our superior trade-off among light-weight, speed, computation and accuracy. Without additional processing and pretraining, LRNNet achieves 72.2% mIoU on Cityscapes test dataset only using the fine annotation data for training with only 0.68M parameters and with 71 FPS on a GTX 1080Ti card.
翻译:最近开发的轻量级神经网络促进了在资源限制和移动应用下深层学习的应用,其中许多应用需要在轻量级网络中对语义分解进行实时和高效的预测,本文件介绍了一个轻量级网络,其高效和实时语义分解的高效非本地模块(LRNNet),我们提议在ResNet-Style编码器中设置一个因子化共进区块,以便实现更轻量级、高效和强大的地物提取。与此同时,我们提议的非本地模块利用空间占支配地位的单个载体,在计算和记忆成本低得多的情况下,实现减少和更具代表性的非本地地物集成。实验表明,我们在轻量级、速度、计算和准确性之间实现了优劣的权衡。没有额外的处理和训练,LRNNet在市景测试数据集上实现了72.2% mIoU,但仅使用精细的注解数据进行培训,只有0.68M参数,GTX 1080T卡上有71 FPS。