22 November 2023 in Neural Networks
19 July 2022 in IEEE Robotics and Automation Letters
While the deep learning-based image deraining methods have made great progress in recent years, there are two major shortcomings in their application in real-world situations. Firstly, the gap between the low-level vision task represented by rain removal and the high-level vision task represented by object detection is significant, and the low-level vision task can hardly contribute to the high-level vision task. Secondly, the quality of the deraining dataset needs to be improved. In fact, the rain lines in many baselines have a large gap with the real rain lines, and the resolution of the deraining dataset images is generally not ideal. Meanwhile, there are few common datasets for both the low-level vision task and the high-level vision task. In this letter, we explore the combination of the low-level vision task with the high-level vision task. Specifically, we propose an end-to-end object detection network for reducing the impact of rainfall, which consists of two cascaded networks, an improved image deraining network and an object detection network, respectively. We also design the components of the loss function to accommodate the characteristics of the different sub-networks. We then propose a dataset based on the KITTI dataset for rainfall removal and object detection, on which our network surpasses the state-of-the-art with a significant improvement in metrics. Besides, our proposed network is measured on driving videos collected by self-driving vehicles and shows positive results for rain removal and object detection.
1 February 1993 in Physical Review A
The global dynamical behavior of a model describing the formation of one-dimensional transverse patterns in a laser has been investigated. Solutions of the equation for the complex electric field are compared to those of a reduced phase equation, the laser Kuramoto-Sivashinsky equation, which should be a good approximation for small detuning. The numerical results show strong evidence of the leading role of the dynamics of the phase of the field in the formation of transverse patterns in a laser with small detuning.
24 September 2022 in Computational Intelligence and Neuroscience
The rain removal method based on CNN develops rapidly. However, convolution operation has the disadvantages of limited receptive field and inadaptability to the input content. Recently, another neural network structure Transformer has shown excellent performance in natural language processing and advanced visual tasks by modeling global relationships, but Transformer has limitations in capturing local dependencies. To address the above limitations, we propose the combination network of CNN and Transformer, which fully combines the advantages of CNN and Transformer structure to complete the task of image restoration. We use CNN to provide preliminary output and adopt Transformer architecture to further optimize the output of CNN. In addition, by using some key designs in module connection, our model strengthens feature propagation and encourages feature reuse, allowing better information and gradient flow. The experimental results show that compared with the existing methods, our method can remove the rain lines more comprehensively and achieve the state-of-the-art results. Besides, the experimental results also demonstrate that the CNN structure can be effectively combined with Transformer to fully utilize the superiority of different structures.
17 July 2023 in Machine Vision and Applications