The range resolution of high-resolution wideband radar is much smaller than the target size. Its echo signals tend to be diverse and sensitive to small changes of targets. Therefore, it is difficult to capture and distinguish the features in radar signals. In this article, we propose a radar target recognition pipeline based on a deep nested neural network. The framework consists of three parts: The translation sensitivity of the training data is first addressed in the preprocessing section. The second step is to obtain an embedded representation of the radar echo signals by the combination of the adjustment layer, convolutional neural network (CNN), and the squeeze and excitation (SE) block. Finally, the target is recognized through inputting embedded representation as a time sequence into the stacked bidirectional recurrent neural network (bi-RNN) based on an attention mechanism. Compared with the traditional methods, the proposed deep nested neural network extracts and takes advantage of the features of radar echo signals more effectively, including the envelope features and local physical structural features. The experimental results based on the test data indicate that the proposed method has a great advantage over other methods in the case of large data sets as well as small training data sets and is robust to the small translation of test samples and noises, exhibiting high engineering practical value.

Unsupervised domain adaptation (UDA) attempts to learn domain invariant representations and has achieved significant progress, whereas self-training-based UDA methods have shown powerful performance. However, due to the domain gap, pseudo-labels selected through high confidence scores or uncertainty inevitably contain noise, leading to inaccurate predictions. To address this issue, we propose a novel risk-consistent training method. Specifically, both clean and noisy classifiers are introduced to estimate the noise transition matrix. The clean classifier is exploited to assign pseudo-labels for target data in each iteration. The noisy classifier is then trained with noisy target samples, and the optimal parameters are obtained through a closed-form solution. Heuristically, we also pre-train a domain predictor to select a target-like source example for the noise transition matrix estimation. In addition, we design an uncertainty-guided regularization to generate soft pseudo-labels and avoid overconfident predictions. Extensive experimental results show the effectiveness of our method, and state-of-the-art performance has been achieved. Codes are available at https://github.com/feifei-cv/RCE.

Real-world images usually contain multiple objects, as a result, generating an image from a multi-instance sketch is an attractive research topic. However, existing generative networks usually produce a similar texture on different instances for those methods focus on learning the distribution of the whole image. To address this problem, we propose a progressive instance texture reserved generative approach to generate more convincible images by decoupling the generation of the instances and the whole image. Specifically, we create an instance generator to synthesize the primitive color distribution and the detailed texture for each instance. Then, an image generator is designed to combine all of these instances to synthesize an image retaining texture and color. Besides, to generate more significant details, such as eyes, ears, and so on, we propose a novel technique called discriminative sketch augmentation, which can provide structural constraint by obtaining the sketch of the discriminative region. The extensive experiments demonstrate that our model not only generates convincing images but also achieves higher inception score and lower Fréchet Inception Distance on the MS-COCO dataset.