The suppression of clutter and the positioning of underground pipelines are crucial steps in the processing of ground-penetrating radar (GPR) data. It is challenging to acquire clutter-free measured data during the radar detection process. As a result, the existing deep learning (DL) methods are primarily trained using simulation data, which limits their applicability to real-world scenarios. To address these challenges, this letter proposes an improved underground clutter suppression and pipeline positioning network. In the first stage, the model is trained using both measured data and simulation clutter-free data to enhance its ability to suppress clutter in measured data. Furthermore, in the second stage, the network is modified to accept paired, labeled simulation data, which enables more accurate pipeline positioning than the original unpaired network. Real-world data evidence demonstrates that the proposed network’s clutter suppression achieves a mean squared error (mse) of 0.006 and a peak signal-to-noise ratio (PSNR) of 34.73 dB. Additionally, the Euclidean distance error of the target clustering center coordinates is 0.82px. Compared to other methods, the performance of the proposed approach has been significantly enhanced.

In this article, we present two fast and interpretable decomposition methods for 2D homography, which are named Similarity-Kernel-Similarity (SKS) and Affine-Core-Affine (ACA) transformations respectively. Under the minimal 4-point configuration, two similarity transformations in SKS are computed by two anchor points on source and target planes, respectively. Then, the other two point correspondences can be exploited to compute the middle kernel transformation with only four parameters. Furthermore, ACA uses three anchor points to compute the source and the target affine transformations, followed by computation of the middle core transformation utilizing the other one point correspondence. ACA can compute a homography up to a scale with only 85 floating-point operations (FLOPs), without even any division operations. Therefore, as a plug-in module, ACA facilitates various traditional feature-based Random Sample Consensus (RANSAC) pipelines, as well as deep homography pipelines estimating 4-point offsets. In addition to the advantages of geometric parameterization and computational efficiency, SKS and ACA can express each element of homography by a polynomial of input coordinates (7th degree to 9th degree), extend the existing essential Similarity-Affine-Projective (SAP) decomposition and calculate 2D affine transformations in a unified way.

Deep learning has brought great progress for the sequential recommendation (SR) tasks. With advanced network architectures, sequential recommender models can be stacked with many hidden layers, e.g., up to 100 layers on real-world recommendation datasets. Training such a deep network is difficult because it can be computationally very expensive and takes much longer time, especially in situations where there are tens of billions of user-item interactions. To deal with such a challenge, we present StackRec, a simple, yet very effective and efficient training framework for deep SR models by iterative layer stacking. Specifically, we first offer an important insight that hidden layers/blocks in a well-trained deep SR model have very similar distributions. Enlightened by this, we propose the stacking operation on the pre-trained layers/blocks to transfer knowledge from a shallower model to a deep model, then we perform iterative stacking so as to yield a much deeper but easier-to-train SR model. We validate the performance of StackRec by instantiating it with four state-of-the-art SR models in three practical scenarios with real-world datasets. Extensive experiments show that StackRec achieves not only comparable performance, but also substantial acceleration in training time, compared to SR models that are trained from scratch. Codes are available at https://github.com/wangjiachun0426/StackRec.