Lightweight Semantic segmentation method based on GhostNet and Atrous Spatial Pyramid Pooling
نویسندگان
چکیده
Abstract Semantic segmentation is frequently utilized in computer vision projects like remote sensing picture segmentation, unmanned driving, and medical image segmentation. A lightweight semantic model suggested by taking into account three components of the network - parameters, calculation, performance to address issue deploying embedded platforms with constrained processing power hardware storage. Dual Attention used Atrous Spatial Pyramid Pooling (ASPP) obtain precise relevant data utilizing GhostNet as foundation, lighten ASPP’s computational burden, depthwise separable convolution used. To a distinct boundary, multi-scale splicing technique then With parameters 2.7810 6 , floating-point calculation 1.931GFLOPs, MIoU 72.13% experiments just on PASCAL VOC 2012, achieves an excellent compromise between efficiency precision.
منابع مشابه
Rethinking Atrous Convolution for Semantic Image Segmentation
In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter’s field-of-view as well as control the resolution of feature responses computed by Deep Convolutional Neural Networks, in the application of semantic image segmentation. To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in paralle...
متن کاملESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
We introduce a fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints. ESPNet is based on a new convolutional module, efficient spatial pyramid (ESP), which is efficient in terms of computation, memory, and power. ESPNet is 22 times faster (on a standard GPU) and 180 times smaller than the stateof-the-art semantic ...
متن کاملEncoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradual...
متن کاملSemantic Segmentation with Second-Order Pooling
Feature extraction, coding and pooling, are important components on many contemporary object recognition paradigms. In this paper we explore novel pooling techniques that encode the second-order statistics of local descriptors inside a region. To achieve this effect, we introduce multiplicative second-order analogues of average and maxpooling that together with appropriate non-linearities lead ...
متن کاملLaplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
CNN architectures have terrific recognition performance but rely on spatial pooling which makes it difficult to adapt them to tasks that require dense, pixel-accurate labeling. This paper makes two contributions: (1) We demonstrate that while the apparent spatial resolution of convolutional feature maps is low, the high-dimensional feature representation contains significant sub-pixel localizat...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of physics
سال: 2023
ISSN: ['0022-3700', '1747-3721', '0368-3508', '1747-3713']
DOI: https://doi.org/10.1088/1742-6596/2477/1/012080