Knowledge Distillation with Fast CNN for License Plate Detection (KDNet) is conducted by Chunwei Tian, Xuanyu Zhang, Xu Liang, Bo Li, Yougang Sun, Shichao Zhang in 2023. It is accepted by the IEEE Transactions on Intelligent Vehicles (SCI-IF:8.2). It is implemented by Pytorch.
Its original paper can be obtained at https://ieeexplore.ieee.org/abstract/document/10309208.
Deep convolutional neural networks (CNNs) with strong expressive ability have achieved impressive performances on single image super-resolution (SISR). However, their excessive amounts ofconvolutions and parameters usually consume high computational cost and more memory storagefor training a SR model, which limits their applications to SR with resource-constrained devicesin real world. To resolve these problems, we propose a lightweight enhanced SR CNN (LESRCNN) with three successive sub-blocks, an information extraction and enhancement block (IEEB), a reconstruction block (RB) and an information refinement block (IRB). Specifically, the IEEB extracts hierarchical low-resolution (LR) features and aggregates the obtained features step-by-step to increase the memory ability of the shallow layers on deep layers for SISR. To remove redundant information obtained, a heterogeneous architecture is adopted in the IEEB. After that, the RB converts low-frequency features into high-frequency features by fusing global and local features, which is complementary with the IEEB in tackling the long-term dependency problem. Finally,the IRB uses coarse high-frequency features from the RB to learn more accurate SR features and construct a SR image. The proposed LESRCNN can obtain a high-quality image by a model fordifferent scales. Extensive experiments demonstrate that the proposed LESRCNN outperforms state-of-the-arts on SISR in terms of qualitative and quantitative evaluation.
The training dataset CCPD is downloaded at (https://github.com/detectRecog/CCPD).
The AOLP dataset is downloaded at (https://github.com/AvLab-CV/AOLP).
The test dataset of CCPD is downloaded at (https://github.com/detectRecog/CCPD).
The test dataset of CLPD is downloaded at (https://github.com/wangpengnorman/CLPD_dataset).
The test dataset of AOLP is downloaded at (https://github.com/AvLab-CV/AOLP).
Download pre-trained yolov7.pt at (https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt).
