Search

Graph kernels are conventional methods for computing graph similarities. However, most of the R-convolution graph kernels face two challenges: 1) They cannot compare graphs at multiple different scales, and 2) they do not consider the distributions of substructures when computing the kernel matrix. These two challenges limit their performances. To mitigate the two challenges, we propose a novel graph kernel called the Multi-scale Path-pattern Graph kernel (MPG), at the heart of which is the multi-scale path-pattern node feature map. Each element of the path-pattern node feature map is the number of occurrences of a path-pattern around a node. A path-pattern is constructed by the concatenation of all the node labels in a path of a truncated BFS tree rooted at each node. Since the path-pattern node feature map can only compare graphs at local scales, we incorporate into it the multiple different scales of the graph structure, which are captured by the truncated BFS trees of different depth. We use the Wasserstein distance to compute the similarity between the multi-scale path-pattern node feature maps of two graphs, considering the distributions of path-patterns. We empirically validate MPG on various benchmark graph datasets and demonstrate that it achieves state-of-the-art performance., 15 pages

This paper aims to solve the problem of estimating the 6D pose of an object under occlusion using RGB-D images. Most existing methods typically use the information of color and depth images separately to make predictions, which limits their performances in the presence of occlusion. Instead, we propose a pipeline to effectively fuse color and depth information and perform region-level pose estimation. Our method first uses a CNN to extract the color features, and then we obtain the fusion features by combining the color features into the point cloud. Unlike existing methods, the fusion features are in the form of point sets instead of feature maps. We further use a PointNet++-like network to process the fusion features, obtaining several region-level features. Each region-level feature can predict a pose with confidence. The pose with the highest confidence is chosen as the final output. Experiments show that the proposed method outperforms the state-of-the-art methods on both the LINEMOD and Occlusion LINEMOD datasets, indicating that the proposed pipeline can obtain accurate pose estimation results and is robust to occlusion.

In product inspection scenarios, the objects have different characteristics of textures and different potential anomalies. Still, traditional methods cannot precisely segment structural anomalies and achieve optimal performance on all object categories. This article introduces a flexible multilevel image reconstruction (MLIR) framework for the unsupervised anomaly segmentation task. The MLIR integrates multiple generators with different downsampling ratios to serve as multiple reconstruction levels and leverage an adjustable perceptual similarity measurement to obtain the featurewise reconstruction errors, overcoming the challenge of detecting multiscale anomalies. Leveraging embeddings with different receptive fields for reconstruction, generators perform differently on the same target. Therefore, we depend on the reconstruction uncertainty to propose an adaptive attention-level transition (ALT) strategy that optimizes the detection performance automatically according to the target’s category. ALT adjusts the weights of both reconstruction levels and feature measurement scales simultaneously to utilize features at a consistent level for reconstruction and anomaly detection (AD). This strategy remarkably improves the system’s adaptivity for different applications. Moreover, we propose reducing the signal-to-noise ratio (SNR) of the images by adding pepper noise so that the reconstruction process is framed as an image denoising task, which improves feature extraction and image restoration robustness. We conduct extensive experiments on the MVTec AD dataset and demonstrate that the proposed method performs satisfactorily to different categories and achieves the state-of-the-art (SOTA) performance.

SUMMARYSelf-localization in highly dynamic environments is still a challenging problem for humanoid robots with limited computation resource. In this paper, we propose a dual-channel unscented particle filter (DC-UPF)-based localization method to address it. A key novelty of this approach is that it employs a dual-channel switch mechanism in measurement updating procedure of particle filter, solving for sparse vision feature in motion, and it leverages data from a camera, a walking odometer, and an inertial measurement unit. Extensive experiments with an NAO robot demonstrate that DC-UPF outperforms UPF and Monte–Carlo localization with regard to accuracy.

Prime editing is a universal and very promising precise genome editing technology. However, optimization of prime editor (PE) from different aspects remains vital for its use as a routine tool in plant basic research and crop molecular breeding. In this report, we tested MS2-based prime editor (MS2PE). We fused the M-MLV reverse transcriptase (RT) gene variant to the MS2 RNA binding protein gene, MCP, and allowed the MCP-RT fusion gene to co-express with the SpCas9 nickase gene, SpCas9H840A, and various engineered pegRNAs harboring MS2 RNA (MS2pegR). Compared with control PEs, MS2PEs significantly enhanced editing efficiency at four of six targets in rice protoplasts, and achieved 1.2~10.1-fold increase in editing efficiency at five of six targets in transgenic rice lines. Furthermore, we tested total 22 different MS2pegR scaffolds, 3 RT variants or genes, 2 MCP variants, and various combinations of the Cas9 nickase, RT, and MCP modules. Our results demonstrated a new strategy for more efficient prime editing and provide a platform for further directed evolution of PEs.