A Kalman-Filter-Incorporated Latent Factor Analysis Model for Temporally Dynamic Sparse Data

Class-Level Logit Perturbation

Features, logits, and labels are the three primary data when a sample passes through a deep neural network (DNN). Feature perturbation and label perturbation receive increasing attention in recent years. They have been proven to be useful in various deep learning approaches. For example, (adversarial) feature perturbation can improve the robustness or even generalization capability of learned models. However, limited studies have explicitly explored for the perturbation of logit vectors. This work discusses several existing methods related to class-level logit perturbation. A unified viewpoint between regular/irregular data augmentation and loss variations incurred by logit perturbation is established. A theoretical analysis is provided to illuminate why class-level logit perturbation is useful. Accordingly, new methodologies are proposed to explicitly learn to perturb logits for both the single-label and multilabel classification tasks. Meta-learning is also leveraged to determine the regular or irregular augmentation for each class. Extensive experiments on benchmark image classification datasets and their long-tail versions indicated the competitive performance of our learning method. As it only perturbs on logit, it can be used as a plug-in to fuse with any existing classification algorithms. All the codes are available at https://github.com/limengyang1992/lpl.

Weighted residual network for SAR automatic target recognition with data augmentation

Introduction

Decades of research have been dedicated to overcoming the obstacles inherent in synthetic aperture radar (SAR) automatic target recognition (ATR). The rise of deep learning technologies has brought a wave of new possibilities, demonstrating significant progress in the field. However, challenges like the susceptibility of SAR images to noise, the requirement for large-scale training datasets, and the often protracted duration of model training still persist.

Methods

This paper introduces a novel data augmentation strategy to address these issues. Our method involves the intentional addition and subsequent removal of speckle noise to artificially enlarge the scope of training data through noise perturbation. Furthermore, we propose a modified network architecture named weighted ResNet, which incorporates residual strain controls for enhanced performance. This network is designed to be computationally efficient and to minimize the amount of training data required.

Results

Through rigorous experimental analysis, our research confirms that the proposed data augmentation method, when used in conjunction with the weighted ResNet model, significantly reduces the time needed for training. It also improves the SAR ATR capabilities.

Discussion

Compared to existing models and methods tested, the combination of our data augmentation scheme and the weighted ResNet framework achieves higher computational efficiency and better recognition accuracy in SAR ATR applications. This suggests that our approach could be a valuable advancement in the field of SAR image analysis.

Real-time depth completion based on LiDAR-stereo for autonomous driving

The integration of multiple sensors is a crucial and emerging trend in the development of autonomous driving technology. The depth image obtained by stereo matching of the binocular camera is easily influenced by environment and distance. The point cloud of LiDAR has strong penetrability. However, it is much sparser than binocular images. LiDAR-stereo fusion can neutralize the advantages of the two sensors and maximize the acquisition of reliable three-dimensional information to improve the safety of automatic driving. Cross-sensor fusion is a key issue in the development of autonomous driving technology. This study proposed a real-time LiDAR-stereo depth completion network without 3D convolution to fuse point clouds and binocular images using injection guidance. At the same time, a kernel-connected spatial propagation network was utilized to refine the depth. The output of dense 3D information is more accurate for autonomous driving. Experimental results on the KITTI dataset showed that our method used real-time techniques effectively. Further, we demonstrated our solution's ability to address sensor defects and challenging environmental conditions using the p-KITTI dataset.