Image classification is a basic task in the field of computer vision, and general image classification task training requires a large amount of labeled data to achieve good generalization performance. However, in practical applications, the cost of obtaining labeled data is expensive. In contrast, unlabeled images are easy to obtain, so semi-supervised image classification is more meaningful for research. This paper pro- poses a framework for semi-supervised classification utilizing multiple self-supervised methods. Our approach is divided into three steps, firstly, pre-train multiple models on unlabeled data using different self-supervised methods. Then use the labeled data to fine-tune these models except the model pre-training by Contrastive learning to obtaining multiple self-supervised teacher models. Finally, the multi-teacher knowledge distillation framework is used to transfer the knowledge of multiple self-supervised teacher models to the model pre-training by contrastive learning to help it achieve further performance. We conducted experiments on cifar10 and miniimagenet60. Our method achieves further results than using only a single self-supervised method, and also achieves superior performance compared to other semi-supervised methods.
Radar communication waveform design is crucial for integrated radar and communication equipment, and abstracts increasing attention. The integrated radar communication waveform is usually faced with a higher sidelobe issue, compared with the single radar waveform, which will reduce the detection performance of radar. In this paper, we propose a convolutional neural network (CNN) based sidelobe suppression method for the integrated radar communication waveform. Different from the conventional method, the proposed method transforms the sidelobe suppression into a signal recognition and classification problem. The simulation results show that when the signal-to-noise ratio is not less than 3dB, this method can make the peak sidelobe ratio of matched filtering reach below -50dB, which has a great improvement compared with the traditional sidelobe suppression method.
Aiming at the problems of low accuracy of bird and drone about radar samples, lack of relevant data, a doppler spectrum recognition method of bird and drone based on one-dimensional deep neural network is proposed. First, take Fourier transform on measured radar echo to acquire the doppler specturm vector of the target, to construct doppler specturm dataset.Then based on the characteristics of the doppler spectrum of bird and drone, design the network structure for doppler spectrum vector of target. To reduce the influence of target flight direction and SNR on accuracy, speed up the training and feature enhancing, the first two layers of network add modulo layer and normalization layer. Then connect the improved one-dimensional ResNet18 to build the entire networks. By training the target doppler specturm samples to get and optimize the final model. Experimental results show that this method can achieve excellent results on bird and drone doppler dataset, with accuracy over 97%.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.