Genetic algorithm assisted meta-atom design for high-performance metasurface optics

Metasurfaces,composed of planar arrays of intricately designed meta-atom structures,possess remarkable capabilities in controlling electromagnetic waves in various ways.A critical aspect of metasurface design involves selecting suitable meta-atoms to achieve target functionalities such as phase retardation,amplitude modulation,and polarization conversion.Conventional design processes often involve extensive parameter sweeping,a laborious and computationally intensive task heavily reliant on designer expertise and judgement.Here,we present an efficient genetic algorithm assisted meta-atom optimization method for high-performance metasurface optics,which is compatible to both single-and multiobjective device design tasks.We first employ the method for a single-objective design task and implement a high-efficiency Pancharatnam-Berry phase based metalens with an average focusing efficiency exceeding 80%in the visible spectrum.We then employ the method for a dual-objective metasurface design task and construct an efficient spin-multiplexed structural beam generator.The device is capable of generating zeroth-order and first-order Bessel beams respectively under right-handed and left-handed circular polarized illumination,with associated generation efficiencies surpassing 88%.Finally,we implement a wavelength and spin co-multiplexed four-channel metahologram capable of projecting two spin-multiplexed holographic images under each operational wavelength,with efficiencies over 50%.Our work offers a streamlined and easy-to-implement approach to meta-atom design and optimization,empowering designers to create diverse high-performance and multifunctional metasurface optics.

C-CORE:Clustering by Code Representation to Prioritize Test Cases in Compiler Testing

Edge devices,due to their limited computational and storage resources,often require the use of compilers for program optimization.Therefore,ensuring the security and reliability of these compilers is of paramount importance in the emerging field of edge AI.One widely used testing method for this purpose is fuzz testing,which detects bugs by inputting random test cases into the target program.However,this process consumes significant time and resources.To improve the efficiency of compiler fuzz testing,it is common practice to utilize test case prioritization techniques.Some researchers use machine learning to predict the code coverage of test cases,aiming to maximize the test capability for the target compiler by increasing the overall predicted coverage of the test cases.Nevertheless,these methods can only forecast the code coverage of the compiler at a specific optimization level,potentially missing many optimization-related bugs.In this paper,we introduce C-CORE(short for Clustering by Code Representation),the first framework to prioritize test cases according to their code representations,which are derived directly from the source codes.This approach avoids being limited to specific compiler states and extends to a broader range of compiler bugs.Specifically,we first train a scaled pre-trained programming language model to capture as many common features as possible from the test cases generated by a fuzzer.Using this pre-trained model,we then train two downstream models:one for predicting the likelihood of triggering a bug and another for identifying code representations associated with bugs.Subsequently,we cluster the test cases according to their code representations and select the highest-scoring test case from each cluster as the high-quality test case.This reduction in redundant testing cases leads to time savings.Comprehensive evaluation results reveal that code representations are better at distinguishing test capabilities,and C-CORE significantly enhances testing efficiency.Across four datasets,C-CORE increases the average of the percentage of faults detected(APFD)value by 0.16 to 0.31 and reduces test time by over 50% in 46% of cases.When compared to the best results from approaches using predicted code coverage,C-CORE improves the APFD value by 1.1% to 12.3% and achieves an overall time-saving of 159.1%.

Learning embeddings of a heterogeneous behavior network for potential behavior prediction

Potential behavior prediction involves understanding the latent human behavior of specific groups,and can assist organizations in making strategic decisions.Progress in information technology has made it possible to acquire more and more data about human behavior.In this paper,we examine behavior data obtained in realworld scenarios as an information network composed of two types of objects(humans and actions)associated with various attributes and three types of relationships(human-human,human-action,and action-action),which we call the heterogeneous behavior network(HBN).To exploit the abundance and heterogeneity of the HBN,we propose a novel network embedding method,human-action-attribute-aware heterogeneous network embedding(a4 HNE),which jointly considers structural proximity,attribute resemblance,and heterogeneity fusion.Experiments on two real-world datasets show that this approach outperforms other similar methods on various heterogeneous information network mining tasks for potential behavior prediction.

Auxiliary diagnostic system for ADHD in children based on AI technology

Traditional diagnosis of attention deficit hyperactivity disorder(ADHD)in children is primarily through a questionnaire filled out by parents/teachers and clinical observations by doctors.It is inefficient and heavily depends on the doctor’s level of experience.In this paper,we integrate artificial intelligence(AI)technology into a software-hardware coordinated system to make ADHD diagnosis more efficient.Together with the intelligent analysis module,the camera group will collect the eye focus,facial expression,3D body posture,and other children’s information during the completion of the functional test.Then,a multi-modal deep learning model is proposed to classify abnormal behavior fragments of children from the captured videos.In combination with other system modules,standardized diagnostic reports can be automatically generated,including test results,abnormal behavior analysis,diagnostic aid conclusions,and treatment recommendations.This system has participated in clinical diagnosis in Department of Psychology,The Children’s Hospital,Zhejiang University School of Medicine,and has been accepted and praised by doctors and patients.

Unsupervised object detection with scene-adaptive concept learning

Object detection is one of the hottest research directions in computer vision,has already made impressive progress in academia,and has many valuable applications in the industry.However,the mainstream detection methods still have two shortcomings:(1)even a model that is well trained using large amounts of data still cannot generally be used across different kinds of scenes;(2)once a model is deployed,it cannot autonomously evolve along with the accumulated unlabeled scene data.To address these problems,and inspired by visual knowledge theory,we propose a novel scene-adaptive evolution unsupervised video object detection algorithm that can decrease the impact of scene changes through the concept of object groups.We first extract a large number of object proposals from unlabeled data through a pre-trained detection model.Second,we build the visual knowledge dictionary of object concepts by clustering the proposals,in which each cluster center represents an object prototype.Third,we look into the relations between different clusters and the object information of different groups,and propose a graph-based group information propagation strategy to determine the category of an object concept,which can effectively distinguish positive and negative proposals.With these pseudo labels,we can easily fine-tune the pretrained model.The effectiveness of the proposed method is verified by performing different experiments,and the significant improvements are achieved.

Detection and segmentation of multi-class artifacts in endoscopy

为准确定位内窥镜视频中的人造物,帮助医生提升诊断准确率,引入深度神经网络检测与分割模型,采用特征金字塔与级联R-CNN相互结合的框架,并使用PSPNet结合分类器链的思想,从而解决分割及数据匮乏问题,有效提升性能,并在EAD 2019数据集上取得领先的性能。

Associative affinity network learning for multi-ob ject tracking

We propose a joint feature and metric learning deep neural network architecture,called the associative affinity network(AAN),as an affinity model for multi-object tracking(MOT)in videos.The AAN learns the associative affinity between tracks and detections across frames in an end-to-end manner.Considering flawed detections,the AAN jointly learns bounding box regression,classification,and affinity regression via the proposed multi-task loss.Contrary to networks that are trained with ranking loss,we directly train a binary classifier to learn the associative affinity of each track-detection pair and use a matching cardinality loss to capture information among candidate pairs.The AAN learns a discriminative affinity model for data association to tackle MOT,and can also perform single-object tracking.Based on the AAN,we propose a simple multi-object tracker that achieves competitive performance on the public MOT16 and MOT17 test datasets.