arXiv subjects

Lei Li

Publications and source records attributed to Lei Li.

At least 505 records · Page 28Linked to original sources

arXiv2023

Unsupervised Cardiac Segmentation Utilizing Synthesized Images from Anatomical Labels

Cardiac segmentation is in great demand for clinical practice. Due to the enormous labor of manual delineation, unsupervised segmentation is desired. The ill-posed optimization problem of this task is inherently challenging, requiring well-designed constraints. In this work, we propose an unsupervised framework for multi-class segmentation with both intensity and shape constraints. Firstly, we extend a conventional non-convex energy function as an intensity constraint and implement it with U-Net. For shape constraint, synthetic images are generated from anatomical labels via image-to-image translation, as shape supervision for the segmentation network. Moreover, augmentation invariance is applied to facilitate the segmentation network to learn the latent features in terms of shape. We evaluated the proposed framework using the public datasets from MICCAI2019 MSCMR Challenge and achieved promising results on cardiac MRIs with Dice scores of 0.5737, 0.7796, and 0.6287 in Myo, LV, and RV, respectively.

eess.IV↗

arXiv2023

BuildSeg: A General Framework for the Segmentation of Buildings

Building segmentation from aerial images and 3D laser scanning (LiDAR) is a challenging task due to the diversity of backgrounds, building textures, and image quality. While current research using different types of convolutional and transformer networks has considerably improved the performance on this task, even more accurate segmentation methods for buildings are desirable for applications such as automatic mapping. In this study, we propose a general framework termed \emph{BuildSeg} employing a generic approach that can be quickly applied to segment buildings. Different data sources were combined to increase generalization performance. The approach yields good results for different data sources as shown by experiments on high-resolution multi-spectral and LiDAR imagery of cities in Norway, Denmark and France. We applied ConvNeXt and SegFormer based models on the high resolution aerial image dataset from the MapAI-competition. The methods achieved an IOU of 0.7902 and a boundary IOU of 0.6185. We used post-processing to account for the rectangular shape of the objects. This increased the boundary IOU from 0.6185 to 0.6189.

cs.CV↗

arXiv2023

Personalized Prompt Learning for Explainable Recommendation

Providing user-understandable explanations to justify recommendations could help users better understand the recommended items, increase the system's ease of use, and gain users' trust. A typical approach to realize it is natural language generation. However, previous works mostly adopt recurrent neural networks to meet the ends, leaving the potentially more effective pre-trained Transformer models under-explored. In fact, user and item IDs, as important identifiers in recommender systems, are inherently in different semantic space as words that pre-trained models were already trained on. Thus, how to effectively fuse IDs into such models becomes a critical issue. Inspired by recent advancement in prompt learning, we come up with two solutions: find alternative words to represent IDs (called discrete prompt learning), and directly input ID vectors to a pre-trained model (termed continuous prompt learning). In the latter case, ID vectors are randomly initialized but the model is trained in advance on large corpora, so they are actually in different learning stages. To bridge the gap, we further propose two training strategies: sequential tuning and recommendation as regularization. Extensive experiments show that our continuous prompt learning approach equipped with the training strategies consistently outperforms strong baselines on three datasets of explainable recommendation.

cs.IR↗

arXiv2023

Multi-Target Landmark Detection with Incomplete Images via Reinforcement Learning and Shape Prior

Medical images are generally acquired with limited field-of-view (FOV), which could lead to incomplete regions of interest (ROI), and thus impose a great challenge on medical image analysis. This is particularly evident for the learning-based multi-target landmark detection, where algorithms could be misleading to learn primarily the variation of background due to the varying FOV, failing the detection of targets. Based on learning a navigation policy, instead of predicting targets directly, reinforcement learning (RL)-based methods have the potential totackle this challenge in an efficient manner. Inspired by this, in this work we propose a multi-agent RL framework for simultaneous multi-target landmark detection. This framework is aimed to learn from incomplete or (and) complete images to form an implicit knowledge of global structure, which is consolidated during the training stage for the detection of targets from either complete or incomplete test images. To further explicitly exploit the global structural information from incomplete images, we propose to embed a shape model into the RL process. With this prior knowledge, the proposed RL model can not only localize dozens of targetssimultaneously, but also work effectively and robustly in the presence of incomplete images. We validated the applicability and efficacy of the proposed method on various multi-target detection tasks with incomplete images from practical clinics, using body dual-energy X-ray absorptiometry (DXA), cardiac MRI and head CT datasets. Results showed that our method could predict whole set of landmarks with incomplete training images up to 80% missing proportion (average distance error 2.29 cm on body DXA), and could detect unseen landmarks in regions with missing image information outside FOV of target images (average distance error 6.84 mm on 3D half-head CT).

cs.CV↗

arXiv2023

VQNet 2.0: A New Generation Machine Learning Framework that Unifies Classical and Quantum

With the rapid development of classical and quantum machine learning, a large number of machine learning frameworks have been proposed. However, existing machine learning frameworks usually only focus on classical or quantum, rather than both. Therefore, based on VQNet 1.0, we further propose VQNet 2.0, a new generation of unified classical and quantum machine learning framework that supports hybrid optimization. The core library of the framework is implemented in C++, and the user level is implemented in Python, and it supports deployment on quantum and classical hardware. In this article, we analyze the development trend of the new generation machine learning framework and introduce the design principles of VQNet 2.0 in detail: unity, practicality, efficiency, and compatibility, as well as full particulars of implementation. We illustrate the functions of VQNet 2.0 through several basic applications, including classical convolutional neural networks, quantum autoencoders, hybrid classical-quantum networks, etc. After that, through extensive experiments, we demonstrate that the operation speed of VQNet 2.0 is higher than the comparison method. Finally, through extensive experiments, we demonstrate that VQNet 2.0 can deploy on different hardware platforms, the overall calculation speed is faster than the comparison method. It also can be mixed and optimized with quantum circuits composed of multiple quantum computing libraries.

quant-ph↗

arXiv2022

Ultrafast switching dynamics of the ferroelectric order in stacking-engineered ferroelectrics

The recently discovered ferroelectricity of van der Waals bilayers offers an unconventional route to improve the performance of devices. Key parameters such as switching field and speed depend on the static and dynamic properties of domain walls (DWs). Here we theoretically explore the properties of textures in stacking-engineered ferroelectrics from first principles. Employing a machine-learning potential model, we present results of large-scale atomistic simulations of stacking DWs and Moiré structure of boron nitride bilayers. We predict that the competition between the switching barrier of stable ferroelectric states and the in-plane lattice distortion leads to a DW width of the order of ten nanometers. DWs motion reduces the critical ferroelectric switching field of a monodomain by two orders of magnitude, while high domain-wall velocities allow domain switching on a picosecond-timescale. The superior performance compared to conventional ferroelectrics (or ferromagnets) may enable ultrafast and power-saving non-volatile memories. By twisting the bilayer into a stacking Moiré structure, the ferroelectric transforms into a super-paraelectric since DWs move under ultralow electric fields.

cond-mat.mtrl-sci↗

arXiv2022

BEATS: An Open-Source, High-Precision, Multi-Channel EEG Acquisition Tool System

Stable and accurate electroencephalogram (EEG) signal acquisition is fundamental in non-invasive brain-computer interface (BCI) technology. Commonly used EEG acquisition system's hardware and software are usually closed-source. Its inability to flexible expansion and secondary development is a major obstacle to real-time BCI research. This paper presents the Beijing University of Posts and Telecommunications EEG Acquisition Tool System named BEATS. It implements a comprehensive system from hardware to software, composed of the analog front-end, microprocessor, and software platform. BEATS is capable of collecting 32-channel EEG signals at a guaranteed sampling rate of 4k Hz with wireless transmission. Compared to state-of-the-art systems used in many EEG fields, it displays a better sampling rate. Using techniques including direct memory access, first in first out, and timer, the precision and stability of the acquisition are ensured at the microsecond level. An evaluation is conducted during 24 hours of continuous acquisitions. The data loss is 0 packets and the average maximum delay is only 0.07 s/h. Moreover, as an open source system, BEATS provides detailed design files, and adopts a plug-in structure and easy-to-access materials, which makes it can be quickly reproduced. Schematics, source code, and other materials of BEATS are available at https://github.com/buptantEEG/BEATS.

eess.SP↗

arXiv2022

Go-tuning: Improving Zero-shot Learning Abilities of Smaller Language Models

With increasing scale, large language models demonstrate both quantitative improvement and new qualitative capabilities, especially as zero-shot learners, like GPT-3. However, these results rely heavily on delicate prompt design and large computation. In this work, we explore whether the strong zero-shot ability could be achieved at a smaller model scale without any external supervised data. To achieve this goal, we revisit masked language modeling and present a geometry-guided self-supervised learning method (Go-tuningfor short) by taking a small number of task-aware self-supervised data to update language models further. Experiments show that Go-tuning can enable T5-small (80M) competitive zero-shot results compared with large language models, such as T5-XL (3B). We also apply Go-tuning on multi-task settings and develop a multi-task model, mgo-T5 (250M). It can reach the average performance of OPT (175B) on 9 datasets.

cs.CL↗

arXiv2022

LR-CSNet: Low-Rank Deep Unfolding Network for Image Compressive Sensing

Deep unfolding networks (DUNs) have proven to be a viable approach to compressive sensing (CS). In this work, we propose a DUN called low-rank CS network (LR-CSNet) for natural image CS. Real-world image patches are often well-represented by low-rank approximations. LR-CSNet exploits this property by adding a low-rank prior to the CS optimization task. We derive a corresponding iterative optimization procedure using variable splitting, which is then translated to a new DUN architecture. The architecture uses low-rank generation modules (LRGMs), which learn low-rank matrix factorizations, as well as gradient descent and proximal mappings (GDPMs), which are proposed to extract high-frequency features to refine image details. In addition, the deep features generated at each reconstruction stage in the DUN are transferred between stages to boost the performance. Our extensive experiments on three widely considered datasets demonstrate the promising performance of LR-CSNet compared to state-of-the-art methods in natural image CS.

cs.CV↗

arXiv2022

Rethinking the Unpretentious U-net for Medical Ultrasound Image Segmentation

Breast tumor segmentation is one of the key steps that helps us characterize and localize tumor regions. However, variable tumor morphology, blurred boundary, and similar intensity distributions bring challenges for accurate segmentation of breast tumors. Recently, many U-net variants have been proposed and widely used for breast tumors segmentation. However, these architectures suffer from two limitations: (1) Ignoring the characterize ability of the benchmark networks, and (2) Introducing extra complex operations increases the difficulty of understanding and reproducing the network. To alleviate these challenges, this paper proposes a simple yet powerful nested U-net (NU-net) for accurate segmentation of breast tumors. The key idea is to utilize U-Nets with different depths and shared weights to achieve robust characterization of breast tumors. NU-net mainly has the following advantages: (1) Improving network adaptability and robustness to breast tumors with different scales, (2) This method is easy to reproduce and execute, and (3) The extra operations increase network parameters without significantly increasing computational cost. Extensive experimental results with twelve state-of-the-art segmentation methods on three public breast ultrasound datasets demonstrate that NU-net has more competitive segmentation performance on breast tumors. Furthermore, the robustness of NU-net is further illustrated on the segmentation of renal ultrasound images. The source code is publicly available on https://github.com/CGPzy/NU-net.

eess.IV↗

arXiv2022

On Analyzing the Role of Image for Visual-enhanced Relation Extraction

Multimodal relation extraction is an essential task for knowledge graph construction. In this paper, we take an in-depth empirical analysis that indicates the inaccurate information in the visual scene graph leads to poor modal alignment weights, further degrading performance. Moreover, the visual shuffle experiments illustrate that the current approaches may not take full advantage of visual information. Based on the above observation, we further propose a strong baseline with an implicit fine-grained multimodal alignment based on Transformer for multimodal relation extraction. Experimental results demonstrate the better performance of our method. Codes are available at https://github.com/zjunlp/DeepKE/tree/main/example/re/multimodal.

cs.CL↗

arXiv2022

MyoPS-Net: Myocardial Pathology Segmentation with Flexible Combination of Multi-Sequence CMR Images

Myocardial pathology segmentation (MyoPS) can be a prerequisite for the accurate diagnosis and treatment planning of myocardial infarction. However, achieving this segmentation is challenging, mainly due to the inadequate and indistinct information from an image. In this work, we develop an end-to-end deep neural network, referred to as MyoPS-Net, to flexibly combine five-sequence cardiac magnetic resonance (CMR) images for MyoPS. To extract precise and adequate information, we design an effective yet flexible architecture to extract and fuse cross-modal features. This architecture can tackle different numbers of CMR images and complex combinations of modalities, with output branches targeting specific pathologies. To impose anatomical knowledge on the segmentation results, we first propose a module to regularize myocardium consistency and localize the pathologies, and then introduce an inclusiveness loss to utilize relations between myocardial scars and edema. We evaluated the proposed MyoPS-Net on two datasets, i.e., a private one consisting of 50 paired multi-sequence CMR images and a public one from MICCAI2020 MyoPS Challenge. Experimental results showed that MyoPS-Net could achieve state-of-the-art performance in various scenarios. Note that in practical clinics, the subjects may not have full sequences, such as missing LGE CMR or mapping CMR scans. We therefore conducted extensive experiments to investigate the performance of the proposed method in dealing with such complex combinations of different CMR sequences. Results proved the superiority and generalizability of MyoPS-Net, and more importantly, indicated a practical clinical application.

eess.IV↗

arXiv2022

Gradient Knowledge Distillation for Pre-trained Language Models

Knowledge distillation (KD) is an effective framework to transfer knowledge from a large-scale teacher to a compact yet well-performing student. Previous KD practices for pre-trained language models mainly transfer knowledge by aligning instance-wise outputs between the teacher and student, while neglecting an important knowledge source, i.e., the gradient of the teacher. The gradient characterizes how the teacher responds to changes in inputs, which we assume is beneficial for the student to better approximate the underlying mapping function of the teacher. Therefore, we propose Gradient Knowledge Distillation (GKD) to incorporate the gradient alignment objective into the distillation process. Experimental results show that GKD outperforms previous KD methods regarding student performance. Further analysis shows that incorporating gradient knowledge makes the student behave more consistently with the teacher, improving the interpretability greatly.

cs.CL↗

arXiv2022

Photometric properties and stellar parameters of the rapidly rotating magnetic early-B star HD 345439

We first present the multicolor photometry results of the rapidly rotating magnetic star HD 345439 using the Nanshan One-meter Wide-field Telescope. From the photometric observations, we derive a rotational period of 0.7699\pm0.0014 day. The light curves of HD 345439 are dominated by the double asymmetric S-wave feature that arises from the magnetic clouds. Pulsating behaviors are not observed in Sector 41 of the Transiting Exoplanet Survey Satellite. No evidence is found of the occurrence of centrifugal breakout events neither in the residual flux nor in the systematic variations at the extremum of the light curve. Based on the hypothesis of the Rigidly Rotating Magnetosphere model, we restrict the magnetic obliquity angle {$β$} and the rotational inclination angle $i$ so that they satisfy the approximate relation {$β+ i \approx 105^{\circ}$}. The colour excess, extinction, and luminosity are determined to be $E_{(B-V)}=0.745\pm0.016\,$mag, $A_{V}=2.31\pm0.05\,$mag, and $\rm log\,(L/L_{\odot})=3.82\pm0.1 $dex, respectively. Furthermore, we derive the effective temperature as $T$$\rm _{eff}=22\pm1 $kK and the surface gravity as log$g=4.00\pm0.22$. The mass$ M=7.24_{-1.24}^{+1.75}\rm M_{\odot}$, radius$ R=4.44_{-1.93}^{+2.68}\rm R_{\odot}$, and age$\rm τ_{age}=23.62\,_{-21.97}^{+4.24} $Myr are estimated from the Hertzsprung--Russell Diagram

astro-ph.SR↗

arXiv2022

Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis

Is it possible to build a general and automatic natural language generation (NLG) evaluation metric? Existing learned metrics either perform unsatisfactorily or are restricted to tasks where large human rating data is already available. We introduce SESCORE, a model-based metric that is highly correlated with human judgements without requiring human annotation, by utilizing a novel, iterative error synthesis and severity scoring pipeline. This pipeline applies a series of plausible errors to raw text and assigns severity labels by simulating human judgements with entailment. We evaluate SESCORE against existing metrics by comparing how their scores correlate with human ratings. SESCORE outperforms all prior unsupervised metrics on multiple diverse NLG tasks including machine translation, image captioning, and WebNLG text generation. For WMT 20/21 En-De and Zh-En, SESCORE improve the average Kendall correlation with human judgement from 0.154 to 0.195. SESCORE even achieves comparable performance to the best supervised metric COMET, despite receiving no human-annotated training data.

cs.CL↗

arXiv2022

On the strict topology of the multipliers of a JB$^*$-algebra

We introduce the Jordan-strict topology on the multipliers algebra of a JB$^*$-algebra, a notion which was missing despite the fourty years passed after the first studies on Jordan multipliers. In case that a C$^*$-algebra $A$ is regarded as a JB$^*$-algebra, the J-strict topology of $M(A)$ is precisely the well-studied C$^*$-strict topology. We prove that every JB$^*$-algebra $\mathfrak{A}$ is J-strict dense in its multipliers algebra $M(\mathfrak{A})$, and that latter algebra is J-strict complete. We show that continuous surjective Jordan homomorphisms, triple homomorphisms, and orthogonality preserving operators between JB$^*$-algebras admit J-strict continuous extensions to the corresponding type of operators between the multipliers algebras. We characterize J-strict continuous functionals on the multipliers algebra of a JB$^*$-algebra $\mathfrak{A}$, and we establish that the dual of $M(\mathfrak{A})$ with respect to the J-strict topology is isometrically isomorphic to $\mathfrak{A}^*$. We also present a first applications of the J-strict topology of the multipliers algebra, by showing that under the extra hypothesis that $\mathfrak{A}$ and $\mathfrak{B}$ are $σ$-unital JB$^*$-algebras, every surjective Jordan $^*$-homomorphism (respectively, triple homomorphism or continuous orthogonality preserving operator) from $\mathfrak{A}$ onto $\mathfrak{B}$ admits an extension to a surjective J-strict continuous Jordan $^*$-homomorphism (respectively, triple homomorphism or continuous orthogonality preserving operator) from $M(\mathfrak{A})$ onto $M(\mathfrak{B})$.

math.OA↗

arXiv2022

On the Relationship between Explanation and Recommendation: Learning to Rank Explanations for Improved Performance

Explaining to users why some items are recommended is critical, as it can help users to make better decisions, increase their satisfaction, and gain their trust in recommender systems (RS). However, existing explainable RS usually consider explanation as a side output of the recommendation model, which has two problems: (1) it is difficult to evaluate the produced explanations because they are usually model-dependent, and (2) as a result, how the explanations impact the recommendation performance is less investigated. In this paper, explaining recommendations is formulated as a ranking task, and learned from data, similar to item ranking for recommendation. This makes it possible for standard evaluation of explanations via ranking metrics (e.g., NDCG). Furthermore, this paper extends traditional item ranking to an item-explanation joint-ranking formalization to study if purposely selecting explanations could reach certain learning goals, e.g., improving recommendation performance. A great challenge, however, is that the sparsity issue in the user-item-explanation data would be inevitably severer than that in traditional user-item interaction data, since not every user-item pair can be associated with all explanations. To mitigate this issue, this paper proposes to perform two sets of matrix factorization by considering the ternary relationship as two groups of binary relationships. Experiments on three large datasets verify the solution's effectiveness on both explanation ranking and item recommendation.

cs.IR↗

arXiv2022

Distillation-Resistant Watermarking for Model Protection in NLP

How can we protect the intellectual property of trained NLP models? Modern NLP models are prone to stealing by querying and distilling from their publicly exposed APIs. However, existing protection methods such as watermarking only work for images but are not applicable to text. We propose Distillation-Resistant Watermarking (DRW), a novel technique to protect NLP models from being stolen via distillation. DRW protects a model by injecting watermarks into the victim's prediction probability corresponding to a secret key and is able to detect such a key by probing a suspect model. We prove that a protected model still retains the original accuracy within a certain bound. We evaluate DRW on a diverse set of NLP tasks including text classification, part-of-speech tagging, and named entity recognition. Experiments show that DRW protects the original model and detects stealing suspects at 100% mean average precision for all four tasks while the prior method fails on two.

cs.CL↗