Search

Vision-based industrial inspection (VII) aims to locate defects quickly and accurately. Supervised learning under a close-set setting and industrial anomaly detection, as two common paradigms in VII, face different problems in practical applications. The former is that various and sufficient defects are difficult to obtain, while the latter is that specific defects cannot be located. To solve these problems, in this paper, we focus on the few-shot semantic segmentation (FSS) method, which can locate unseen defects conditioned on a few annotations without retraining. Compared to common objects in natural images, the defects in VII are small. This brings two problems to current FSS methods: 1 distortion of target semantics and 2 many false positives for backgrounds. To alleviate these problems, we propose a small object few-shot segmentation (SOFS) model. The key idea for alleviating 1 is to avoid the resizing of the original image and correctly indicate the intensity of target semantics. SOFS achieves this idea via the non-resizing procedure and the prototype intensity downsampling of support annotations. To alleviate 2, we design an abnormal prior map in SOFS to guide the model to reduce false positives and propose a mixed normal Dice loss to preferentially prevent the model from predicting false positives. SOFS can achieve FSS and few-shot anomaly detection determined by support masks. Diverse experiments substantiate the superior performance of SOFS. Code is available at https://github.com/zhangzilongc/SOFS.

Learning a universal manipulation policy encompassing doors with diverse categories, geometries and mechanisms, is crucial for future embodied agents to effectively work in complex and broad real-world scenarios. Due to the limited datasets and unrealistic simulation environments, previous works fail to achieve good performance across various doors. In this work, we build a novel door manipulation environment reflecting different realistic door manipulation mechanisms, and further equip this environment with a large-scale door dataset covering 6 door categories with hundreds of door bodies and handles, making up thousands of different door instances. Additionally, to better emulate real-world scenarios, we introduce a mobile robot as the agent and use the partial and occluded point cloud as the observation, which are not considered in previous works while possessing significance for real-world implementations. To learn a universal policy over diverse doors, we propose a novel framework disentangling the whole manipulation process into three stages, and integrating them by training in the reversed order of inference. Extensive experiments validate the effectiveness of our designs and demonstrate our framework's strong performance. Code, data and videos are avaible on https://unidoormanip.github.io/., Comment: Project page https://unidoormanip.github.io/

Electromagnetic radiation at higher harmonics of the plasma frequency ($\omega \sim n\omega_{pe}, n > 2$) has been occasionally observed in type II and type III solar radio bursts, yet the underlying mechanism remains undetermined. Here we present two-dimensional fully kinetic electromagnetic particle-in-cell simulations with high spectral resolution to investigate the beam-driven plasma emission process in weakly magnetized plasmas of typical coronal conditions. We focused on the generation mechanisms of high-harmonic emission. We found that a larger beam velocity ($u_d$) favors the generation of the higher-harmonic emission. The emissions grow later for higher harmonics and decrease in intensity by $\sim$2 orders of magnitude for each jump of the harmonic number. The second and third harmonic ($\rm H_2$ and $\rm H_3$) emissions get closer in intensity with larger $u_d$. We also show that (1) the $\rm H_3$ emission is mainly generated via the coalescence of the $\rm H_2$ emission with the Langmuir waves, i.e., $\rm H_2 + L \rightarrow H_3$, wherein the coalescence with the forward-propagating beam-Langmuir wave leads to the forward-propagating $\rm H_3$, and coalescence with the backward-propagating Langmuir wave leads to the backward-propagating $\rm H_3$; and (2) the $\rm H_4$ emission mainly arises from the coalescence of the $\rm H_3$ emission with the forward- (backward-) propagating Langmuir wave, in terms of $\rm H_3 + L \rightarrow H_4$.

One-class classification (OCC), i.e., identifying whether an example belongs to the same distribution as the training data, is essential for deploying machine learning models in the real world. Adapting the pre-trained features on the target dataset has proven to be a promising paradigm for improving OCC performance. Existing methods are constrained by assumptions about the number of classes. This contradicts the real scenario where the number of classes is unknown. In this work, we propose a simple class-agnostic adaptive feature adaptation method (CA2). We generalize the center-based method to unknown classes and optimize this objective based on the prior existing in the pre-trained network, i.e., pre-trained features that belong to the same class are adjacent. CA2 is validated to consistently improve OCC performance across a spectrum of training data classes, spanning from 1 to 1024, outperforming current state-of-the-art methods. Code is available at https://github.com/zhangzilongc/CA2., Comment: Submit to AAAI 2024

Biological networks are commonly used in biomedical and healthcare domains to effectively model the structure of complex biological systems with interactions linking biological entities. However, due to their characteristics of high dimensionality and low sample size, directly applying deep learning models on biological networks usually faces severe overfitting. In this work, we propose R-MIXUP, a Mixup-based data augmentation technique that suits the symmetric positive definite (SPD) property of adjacency matrices from biological networks with optimized training efficiency. The interpolation process in R-MIXUP leverages the log-Euclidean distance metrics from the Riemannian manifold, effectively addressing the swelling effect and arbitrarily incorrect label issues of vanilla Mixup. We demonstrate the effectiveness of R-MIXUP with five real-world biological network datasets on both regression and classification tasks. Besides, we derive a commonly ignored necessary condition for identifying the SPD matrices of biological networks and empirically study its influence on the model performance. The code implementation can be found in Appendix E., Comment: Accepted to KDD 2023

Industrial anomaly detection (IAD) is crucial for automating industrial quality inspection. The diversity of the datasets is the foundation for developing comprehensive IAD algorithms. Existing IAD datasets focus on the diversity of data categories, overlooking the diversity of domains within the same data category. In this paper, to bridge this gap, we propose the Aero-engine Blade Anomaly Detection (AeBAD) dataset, consisting of two sub-datasets: the single-blade dataset and the video anomaly detection dataset of blades. Compared to existing datasets, AeBAD has the following two characteristics: 1.) The target samples are not aligned and at different scales. 2.) There is a domain shift between the distribution of normal samples in the test set and the training set, where the domain shifts are mainly caused by the changes in illumination and view. Based on this dataset, we observe that current state-of-the-art (SOTA) IAD methods exhibit limitations when the domain of normal samples in the test set undergoes a shift. To address this issue, we propose a novel method called masked multi-scale reconstruction (MMR), which enhances the model's capacity to deduce causality among patches in normal samples by a masked reconstruction task. MMR achieves superior performance compared to SOTA methods on the AeBAD dataset. Furthermore, MMR achieves competitive performance with SOTA methods to detect the anomalies of different types on the MVTec AD dataset. Code and dataset are available at https://github.com/zhangzilongc/MMR., Comment: Accept by Computers in Industry

According to the standard scenario of plasma emission, escaping radiations are generated by the nonlinear development of the kinetic bump-on-tail instability driven by a single beam of energetic electrons interacting with plasmas. Here we conduct fully-kinetic electromagnetic particle-in-cell simulations to investigate plasma emission induced by the ring-distributed energetic electrons interacting with overdense plasmas. Efficient excitations of the fundamental (F) and harmonic (H) emissions are revealed with radiation mechanism(s) different from the standard scenario: (1) The primary modes accounting for the radiations are generated through the electron cyclotron maser instability (for the upper-hybrid (UH) and Z modes) and the thermal anisotropic instability (for the whistler (W) mode); the F emission is generated by the nonlinear coupling of the Z and W modes and the H emission by the nonlinear coupling of the UH modes. This presents an alternative mechanism of coherent radiation in overdense plasmas.

Human brains are commonly modeled as networks of Regions of Interest (ROIs) and their connections for the understanding of brain functions and mental disorders. Recently, Transformer-based models have been studied over different types of data, including graphs, shown to bring performance gains widely. In this work, we study Transformer-based models for brain network analysis. Driven by the unique properties of data, we model brain networks as graphs with nodes of fixed size and order, which allows us to (1) use connection profiles as node features to provide natural and low-cost positional information and (2) learn pair-wise connection strengths among ROIs with efficient attention weights across individuals that are predictive towards downstream analysis tasks. Moreover, we propose an Orthonormal Clustering Readout operation based on self-supervised soft clustering and orthonormal projection. This design accounts for the underlying functional modules that determine similar behaviors among groups of ROIs, leading to distinguishable cluster-aware node embeddings and informative graph embeddings. Finally, we re-standardize the evaluation pipeline on the only one publicly available large-scale brain network dataset of ABIDE, to enable meaningful comparison of different models. Experiment results show clear improvements of our proposed Brain Network Transformer on both the public ABIDE and our restricted ABCD datasets. The implementation is available at https://github.com/Wayfear/BrainNetworkTransformer., Comment: Accepted to NeurIPS 2022. The previous version is accepted for Workshop ICML-IMLH 2022 (Oral, no proceedings)

The standard theory of plasma emission is based on kinetic couplings between a single beam of energetic electrons and unmagnetized thermal plasmas, involving multi-step nonlinear wave-particle and wave-wave interactions. The theory has not yet been completely verified with fully-kinetic electromagnetic particle-in-cell (PIC) simulations. Earlier studies, greatly limited by available computational resources, are controversial regarding whether the fundamental emission can be generated according to the standard theory. To resolve the controversy, we conducted PIC simulations with a large domain of simulation and a large number of macroparticles, among the largest ones of similar studies. We found significant fundamental emission if the relative beam density is small enough (say, $\le$ 0.01), in line with earlier study with a much-smaller domain; the relative intensity (normalized by the total initial beam energy) of all modes, except the mode associated with the beam-electromagnetic Weibel instability, decreases with increasing relative density of the beam. We also found significant transverse magnetic component associated with the superluminal Langmuir turbulence, which has been mistakenly regarded as evidence of the F emission in earlier study. Further investigations are required to reveal their origin.

In laser-based free-space optical communication, besides OAM beams, Hermite-Gaussian (HG) modes or HG-mode coherently composed states (HG-MCCS) can also be adopted as the information carrier to extend the channel capacity with the spatial pattern based encoding and decoding link. The light field of HG-MCCS is mainly determined by three independent parameters, including indexes of HG modes, relative initial phases between two eigenmodes, and scale coefficients of the eigenmodes, which can obtain a large number of effective coding modes at a low mode order. The beam intensity distributions of the HG-MCCSs have obvious distinguishable spatial characteristics and can keep propagation invariance, which are convenient to be decoded by the convolutional neural network (CNN) based image recognition method. We experimentally utilize HG-MCCS to realize a communication link including encoding, transmission under atmospheric turbulence (AT), and decoding based on CNN. With the index order of eigenmodes within six, 125 HG-MCCS are generated and used for information encoding, and the average recognition accuracy reached 99.5% for non-AT conditions. For the 125-level color images transmission, the error rate of the system is less than 1.8% even under the weak AT condition. Our work provides a useful basis for the future combination of dense data communication and artificial intelligence technology.

Previous studies on the beam-driven plasma emission process were done mainly for unmagnetized plasmas. Here we present fully-kinetic electromagnetic particle-in-cell simulations to investigate such process in weakly-magnetized plasmas of the solar corona conditions. The primary mode excited is the beam-Langmuir (BL) mode via the classical bump-on-tail instability. Other modes include the whistler (W) mode excited by the electron cyclotron resonance instability, the generalized Langmuir (GL) waves that include a superluminal Z-mode component with smaller wave number $k$ and a thermal Langmuir component with larger $k$, and the fundamental (F) and harmonic (H) branches of plasma emission. Further simulations of different mass and temperature ratios of electrons and protons indicate that the GL mode and the two escaping modes (F and H) correlate positively with the BL mode in intensity, supporting that they are excited through nonlinear wave-wave coupling processes involving the BL mode. We suggest that the dominant process is the decay of the primary BL mode. This is consistent with the standard theory of plasma emission. Yet, the other possibility of the Z+W$\rightarrow$O--F coalescing process for the F emission cannot be ruled out completely.

The self-healing property of laser beams is of great interest. And a laser beam with spatial structures is also widely concerned due to its important applications in lots of areas. We theoretically and experimentally investigate the self-healing and transformation characteristics of obstructed structured beams composed by incoherent or coherent superposition of multiple Hermite-Gaussian (HG) modes. We reveal that partially obstructed single HG mode can recover itself or transfer to a lower order in the far-field. When the obstacle retains one pair of edged bright spots of HG mode in each direction of its two symmetry axes, the beam structure information (number of knot lines) along each axis can be restored. Otherwise, it will be transferred to the corresponding low-order HG mode or multi interference fringes in the far-field, according to the interval of the two most edged remaining spots on each axis. It's proved that the above effect is induced by the diffraction and interference results of the partially retained light field. This principle is also applicable to multi-eigenmodes composed beams with special customized optical structures. Then the self-healing and transformation characteristics of the partially obstructed HG modes composed structured beams are investigated. It's found that the HG modes incoherently composed structured beams have a strong ability to recover themselves in the far-field after occlusion. These investigations can expand the applications of optical lattice structures of laser communication, atom optical capture, and optical imaging.