Figure - available from: International Journal of Machine Learning and Cybernetics
This content is subject to copyright. Terms and conditions apply.
Diagram of the different backbone architectures. Both a and b are encoder-decoder networks, but b adds additional lateral connections to recover high-resolution feature maps. c is the proposed bilateral crack detection model. The green module represents the detail branch and the yellow one represents the semantic branch
Source publication
Crack detection is an important task to ensure structural safety. Traditional manual detection is extremely time-consuming and labor-intensive. However, existing deep learning-based methods also commonly suffer from low inference speed and continuous crack interruption. To solve the above problems, a novel bilateral crack detection network (BiCrack...
Similar publications
![Different feature distillation modules. a The architecture of IMDB [1]....](publication/386143182/figure/fig1/AS:11431281298384041@1734404342569/Different-feature-distillation-modules-a-The-architecture-of-IMDB-1-b-The_Q320.jpg)
![Visual comparisons of CFDN with other ×\documentclass[12pt]{minimal}...](publication/386143182/figure/fig5/AS:11431281298291584@1734404343277/Visual-comparisons-of-CFDN-with-other-documentclass12ptminimal-usepackageamsmath_Q320.jpg)
Feature distillation plays an important role in lightweight single image super-resolution (SISR) by retaining and extracting hierarchical features step-by-step. This allows the network to possess a deep and compact structure, enabling it to achieve lightweight while maintaining good performance. However, the features prematurely retained by the dis...
