Unsupervised anomaly detection and localization is crucial to the practical application when collecting and labeling sufficient anomaly data is infeasible. Most existing representation-based approaches extract normal image features with a deep convolutional neural network and characterize the corresponding distribution through non-parametric distribution estimation methods. The anomaly score is calculated by measuring the distance between the feature of the test image and the estimated distribution. However, current methods can not effectively map image features to a tractable base distribution and ignore the relationship between local and global features which are important to identify anomalies. To this end, we propose FastFlow implemented with 2D normalizing flows and use it as the probability distribution estimator. Our FastFlow can be used as a plug-in module with arbitrary deep feature extractors such as ResNet and vision transformer for unsupervised anomaly detection and localization. In training phase, FastFlow learns to transform the input visual feature into a tractable distribution and obtains the likelihood to recognize anomalies in inference phase. Extensive experimental results on the MVTec AD dataset show that FastFlow surpasses previous state-of-the-art methods in terms of accuracy and inference efficiency with various backbone networks. Our approach achieves 99.4% AUC in anomaly detection with high inference efficiency.

No abstract

Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned from a fully labeled source domain to a scarcely labeled target domain. In this paper, we propose a Multi-level Consistency Learning (MCL) framework for SSDA. Specifically, our MCL regularizes the consistency of different views of target domain samples at three levels: (i) at inter-domain level, we robustly and accurately align the source and target domains using a prototype-based optimal transport method that utilizes the pros and cons of different views of target samples; (ii) at intra-domain level, we facilitate the learning of both discriminative and compact target feature representations by proposing a novel classwise contrastive clustering loss; (iii) at sample level, we follow standard practice and improve the prediction accuracy by conducting a consistencybased self-training. Empirically, we verified the effectiveness of our MCL framework on three popular SSDA benchmarks, i.e., VisDA2017, Domain-Net, and Office-Home datasets, and the experimental results demonstrate that our MCL framework achieves the state-of-the-art performance.

Graph Neural Networks (GNNs) have gained momentum in graph representation learning and boosted the state of the art in a variety of areas, such as data mining (e.g., social network analysis and recommender systems), computer vision (e.g., object detection and point cloud learning), and natural language processing (e.g., relation extraction and sequence learning), to name a few. With the emergence of Transformers in natural language processing and computer vision, graph Transformers embed a graph structure into the Transformer architecture to overcome the limitations of local neighborhood aggregation while avoiding strict structural inductive biases. In this paper, we present a comprehensive review of GNNs and graph Transformers in computer vision from a task-oriented perspective. Specifically, we divide their applications in computer vision into five categories according to the modality of input data, i.e., 2D natural images, videos, 3D data, vision + language, and medical images. In each category, we further divide the applications according to a set of vision tasks. Such a task-oriented taxonomy allows us to examine how each task is tackled by different GNN-based approaches and how well these approaches perform. Based on the necessary preliminaries, we provide the definitions and challenges of the tasks, in-depth coverage of the representative approaches, as well as discussions regarding insights, limitations, and future directions.

Light-driven synthetic biology refers to an autotrophic microorganisms-based research platform that remodels microbial metabolism through synthetic biology and directly converts light energy into bio-based chemicals. This technology can help achieve the goal of carbon neutrality while promoting green production. Cyanobacteria are photosynthetic microorganisms that use light and CO2 for growth and production. They thus possess unique advantages as “autotrophic cell factories”. Various fuels and chemicals have been synthesized by cyanobacteria, indicating their important roles in research and industrial application. This review summarized the progresses and remaining challenges in light-driven cyanobacterial cell factory. The choice of chassis cells, strategies used in metabolic engineering, and the methods for high-value CO2 utilization will be discussed.

Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervised scheme with only sparse points annotated. Existing works start from the given labels and propagate them to highly-related but unlabeled points, with the guidance of data, e.g. intra-point relation. However, it suffers from (i) the inefficient exploitation of data information, and (ii) the strong reliance on labels thus is easily suppressed when given much fewer annotations. Therefore, we propose a novel framework, PointMatch, that stands on both data and label, by applying consistency regularization to sufficiently probe information from data itself and leveraging weak labels as assistance at the same time. By doing so, meaningful information can be learned from both data and label for better representation learning, which also enables the model more robust to the extent of label sparsity. Simple yet effective, the proposed PointMatch achieves the state-of-theart performance under various weakly-supervised schemes on both ScanNet-v2 and S3DIS datasets, especially on the settings with extremely sparse labels, e.g. surpassing SQN by 21.2% and 17.2% on the 0.01% and 0.1% setting of ScanNet-v2, respectively.

Purpose This paper aims to study a new halogen-free fame-retardant curing agent 1-aminoethylidenediphosphonate (AAEDP). Design/methodology/approach The AAEDP was synthesized by phosphoric acid, acetonitrile and ammonia. The chemical structures of AAEDP were characterized by proton nuclear magnetic resonance, mass spectrometry and Fourier transform infrared spectrometer. Thermal gravimetric analysis (TGA) and scanning electron microscope (SEM) would study the thermal properties and the char residues of AAEDP/EP. The thermal stability, mechanical and flame properties and morphology for the char layer of composite materials were separately investigated using TGA, tensile and charpy impact tests, limiting oxygen index (LOI), UL-94 HB flammability standard (UL-94) and SEM. Findings The results showed that the AAEDP had been prepared successfully. When the intumescent flame retardant was added into the EP, the LOI of composite material was improved. Research limitations/implications The AAEDP can be prepared successfully and can improve the flame resistance of composite material. Practical implications The AAEDP has excellent flame-retardant properties and produce no toxic fumes when burnt in case of fire. Originality/value The results showed that the phosphorus content of AAEDP was 2.958 Wt.%; the impact and tensile strength of the composite material were 6.417 kJ m−2 and 38.0 MPa, respectively; and the LOI and UL-94 were 29.7% and V-0 ranking, respectively. The TGA results indicated that the carbon residue ratio can be increased by 1000°C in air. The denser and more uniform structure of residual carbon prevents heat transfer and diffusion, restricts the production of combustible gas and reduces the rate of heat release.

No abstract