Micromotors, which can be moved at a micron scale, have special functions and can perform microscopic tasks. They have a wide range of applications in various fields with the advantages of small size and high efficiency. Both high speed and efficiency for micromotors are required in various conditions. However, the dynamical mechanism of bubble-driven micromotors movement is not clear, owing to various factors affecting the movement of micromotors. This paper reviews various factors acting on micromotor movement, and summarizes appropriate methods to improve the velocity and efficiency of bubble-driven micromotors, from a mechanical view. The dynamical factors that have significant influence on the hydrodynamic performance of micromotors could be divided into two categories: environment and geometry. Improving environment temperature and decreasing viscosity of fluid accelerate the velocity of motors. Under certain conditions, raising the concentration of hydrogen peroxide is applied. However, a high concentration of hydrogen peroxide is not applicable. In the environment of low concentration, changing the geometry of micromotors is an effective mean to improve the velocity of micromotors. Increasing semi-cone angle and reducing the ratio of length to radius for tubular and rod micromotors are propitious to increase the speed of micromotors. For Janus micromotors, reducing the mass by changing the shape into capsule and shell, and increasing the surface roughness, is applied. This review could provide references for improving the velocity and efficiency of micromotors.
Real-world applications have high demands for semantic segmentation methods. Although semantic segmentation has made remarkable leap-forwards with deep learning, the performance of real-time methods is not satisfactory. In this work, we propose PP-LiteSeg, a novel lightweight model for the real-time semantic segmentation task. Specifically, we present a Flexible and Lightweight Decoder (FLD) to reduce computation overhead of previous decoder. To strengthen feature representations, we propose a Unified Attention Fusion Module (UAFM), which takes advantage of spatial and channel attention to produce a weight and then fuses the input features with the weight. Moreover, a Simple Pyramid Pooling Module (SPPM) is proposed to aggregate global context with low computation cost. Extensive evaluations demonstrate that PP-LiteSeg achieves a superior tradeoff between accuracy and speed compared to other methods. On the Cityscapes test set, PP-LiteSeg achieves 72.0% mIoU/273.6 FPS and 77.5% mIoU/102.6 FPS on NVIDIA GTX 1080Ti. Source code and models are available at Pad-dleSeg: https://github.com/PaddlePaddle/PaddleSeg.
The better accuracy and efficiency trade-off has been a challenging problem in object detection. In this work, we are dedicated to studying key optimizations and neural network architecture choices for object detection to improve accuracy and efficiency. We investigate the applicability of the anchor-free strategy on lightweight object detection models. We enhance the backbone structure and design the lightweight structure of the neck, which improves the feature extraction ability of the network. We improve label assignment strategy and loss function to make training more stable and efficient. Through these optimizations, we create a new family of real-time object detectors, named PP-PicoDet, which achieves superior performance on object detection for mobile devices. Our models achieve better trade-offs between accuracy and latency compared to other popular models. PicoDet-S with only 0.99M parameters achieves 30.6% mAP, which is an absolute 4.8% improvement in mAP while reducing mobile CPU inference latency by 55% compared to YOLOX-Nano, and is an absolute 7.1% improvement in mAP compared to NanoDet. It reaches 123 FPS (150 FPS using Paddle Lite) on mobile ARM CPU when the input size is 320. PicoDet-L with only 3.3M parameters achieves 40.9% mAP, which is an absolute 3.7% improvement in mAP and 44% faster than YOLOv5s. As shown in Figure 1, our models far outperform the stateof-the-art results for lightweight object detection. Code and pre-trained models are available at PaddleDetection 1 .
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.