LRNNet: A Light-Weighted Network with Efficient Reduced Non-Local Operation for Real-Time Semantic Segmentation
This addresses the need for efficient and real-time semantic segmentation in resource-constrained applications like mobile devices, though it is incremental as it builds on existing light-weighted network designs.
The paper tackles real-time semantic segmentation by proposing LRNNet, a light-weighted network with an efficient reduced non-local module, achieving 72.2% mIoU on Cityscapes with only 0.68M parameters and 71 FPS on a GTX 1080Ti.
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.