Surgical instrument segmentation in laparoscopy is essential for computer-assisted surgical systems. Despite the Deep Learning progress in recent years, the dynamic setting of laparoscopic surgery still presents challenges for precise segmentation. The nnU-Net framework excelled in semantic segmentation analyzing single frames without temporal information. The framework's ease of use, including its ability to be automatically configured, and its low expertise requirements, have made it a popular base framework for comparisons. Optical flow (OF) is a tool commonly used in video tasks to estimate motion and represent it in a single frame, containing temporal information. This work seeks to employ OF maps as an additional input to the nnU-Net architecture to improve its performance in the surgical instrument segmentation task, taking advantage of the fact that instruments are the main moving objects in the surgical field. With this new input, the temporal component would be indirectly added without modifying the architecture. Using CholecSeg8k dataset, three different representations of movement were estimated and used as new inputs, comparing them with a baseline model. Results showed that the use of OF maps improves the detection of classes with high movement, even when these are scarce in the dataset. To further improve performance, future work may focus on implementing other OF-preserving augmentations.
相關內容
Information Extraction processes in handwritten documents tend to rely on obtaining an automatic transcription and performing Named Entity Recognition (NER) over such transcription. For this reason, in publicly available datasets, the performance of the systems is usually evaluated with metrics particular to each dataset. Moreover, most of the metrics employed are sensitive to reading order errors. Therefore, they do not reflect the expected final application of the system and introduce biases in more complex documents. In this paper, we propose and publicly release a set of reading order independent metrics tailored to Information Extraction evaluation in handwritten documents. In our experimentation, we perform an in-depth analysis of the behavior of the metrics to recommend what we consider to be the minimal set of metrics to evaluate a task correctly.
Ontology and knowledge graph matching systems are evaluated annually by the Ontology Alignment Evaluation Initiative (OAEI). More and more systems use machine learning-based approaches, including large language models. The training and validation datasets are usually determined by the system developer and often a subset of the reference alignments are used. This sampling is against the OAEI rules and makes a fair comparison impossible. Furthermore, those models are trained offline (a trained and optimized model is packaged into the matcher) and therefore the systems are specifically trained for those tasks. In this paper, we introduce a dataset that contains training, validation, and test sets for most of the OAEI tracks. Thus, online model learning (the systems must adapt to the given input alignment without human intervention) is made possible to enable a fair comparison for ML-based systems. We showcase the usefulness of the dataset by fine-tuning the confidence thresholds of popular systems.
Efficient and robust anisotropic mesh adaptation is crucial for Computational Fluid Dynamics (CFD) simulations. The CFD Vision 2030 Study highlights the pressing need for this technology, particularly for simulations targeting supercomputers. This work applies a fine-grained speculative approach to anisotropic mesh operations. Our implementation exhibits more than 90% parallel efficiency on a multi-core node. Additionally, we evaluate our method within an adaptive pipeline for a spectrum of publicly available test-cases that includes both analytically derived and error-based fields. For all test-cases, our results are in accordance with published results in the literature. Support for CAD-based data is introduced, and its effectiveness is demonstrated on one of NASA's High-Lift prediction workshop cases.
This study introduces a computational approach leveraging Physics-Informed Neural Networks (PINNs) for the efficient computation of arterial blood flows, particularly focusing on solving the incompressible Navier-Stokes equations by using the domain decomposition technique. Unlike conventional computational fluid dynamics methods, PINNs offer advantages by eliminating the need for discretized meshes and enabling the direct solution of partial differential equations (PDEs). In this paper, we propose the weighted Extended Physics-Informed Neural Networks (WXPINNs) and weighted Conservative Physics-Informed Neural Networks (WCPINNs), tailored for detailed hemodynamic simulations based on generalized space-time domain decomposition techniques. The inclusion of multiple neural networks enhances the representation capacity of the weighted PINN methods. Furthermore, the weighted PINNs can be efficiently trained in parallel computing frameworks by employing separate neural networks for each sub-domain. We show that PINNs simulation results circumvent backflow instabilities, underscoring a notable advantage of employing PINNs over traditional numerical methods to solve such complex blood flow models. They naturally address such challenges within their formulations. The presented numerical results demonstrate that the proposed weighted PINNs outperform traditional PINNs settings, where sub-PINNs are applied to each subdomain separately. This study contributes to the integration of deep learning methodologies with fluid mechanics, paving the way for accurate and efficient high-fidelity simulations in biomedical applications, particularly in modeling arterial blood flow.
Recent advances in deep learning algorithms have shown impressive progress in image copy-move forgery detection (CMFD). However, these algorithms lack generalizability in practical scenarios where the copied regions are not present in the training images, or the cloned regions are part of the background. Additionally, these algorithms utilize convolution operations to distinguish source and target regions, leading to unsatisfactory results when the target regions blend well with the background. To address these limitations, this study proposes a novel end-to-end CMFD framework that integrates the strengths of conventional and deep learning methods. Specifically, the study develops a deep cross-scale PatchMatch (PM) method that is customized for CMFD to locate copy-move regions. Unlike existing deep models, our approach utilizes features extracted from high-resolution scales to seek explicit and reliable point-to-point matching between source and target regions. Furthermore, we propose a novel pairwise rank learning framework to separate source and target regions. By leveraging the strong prior of point-to-point matches, the framework can identify subtle differences and effectively discriminate between source and target regions, even when the target regions blend well with the background. Our framework is fully differentiable and can be trained end-to-end. Comprehensive experimental results highlight the remarkable generalizability of our scheme across various copy-move scenarios, significantly outperforming existing methods.
This work initiates the study of a beyond-diagonal reconfigurable intelligent surface (BD-RIS)-aided transmitter architecture for integrated sensing and communication (ISAC) in the millimeter-wave (mmWave) frequency band. Deploying BD-RIS at the transmitter side not only alleviates the need for extensive fully digital radio frequency (RF) chains but also enhances both communication and sensing performance. These benefits are facilitated by the additional design flexibility introduced by the fully-connected scattering matrix of BD-RIS. To achieve the aforementioned benefits, in this work, we propose an efficient two-stage algorithm to design the digital beamforming of the transmitter and the scattering matrix of the BD-RIS with the aim of jointly maximizing the sum rate for multiple communication users and minimizing the largest eigenvalue of the Cramer-Rao bound (CRB) matrix for multiple sensing targets. Numerical results show that the transmitter-side BD-RIS-aided mmWave ISAC outperforms the conventional diagonal-RIS-aided ones in both communication and sensing performance.
We provide in this work an algorithm for approximating a very broad class of symmetric Toeplitz matrices to machine precision in $\mathcal{O}(n \log n)$ time. In particular, for a Toeplitz matrix $\mathbf{\Sigma}$ with values $\mathbf{\Sigma}_{j,k} = h_{|j-k|} = \int_{-1/2}^{1/2} e^{2 \pi i |j-k| \omega} S(\omega) \mathrm{d} \omega$ where $S(\omega)$ is piecewise smooth, we give an approximation $\mathbf{\mathcal{F}} \mathbf{\Sigma} \mathbf{\mathcal{F}}^H \approx \mathbf{D} + \mathbf{U} \mathbf{V}^H$, where $\mathbf{\mathcal{F}}$ is the DFT matrix, $\mathbf{D}$ is diagonal, and the matrices $\mathbf{U}$ and $\mathbf{V}$ are in $\mathbb{C}^{n \times r}$ with $r \ll n$. Studying these matrices in the context of time series, we offer a theoretical explanation of this structure and connect it to existing spectral-domain approximation frameworks. We then give a complete discussion of the numerical method for assembling the approximation and demonstrate its efficiency for improving Whittle-type likelihood approximations, including dramatic examples where a correction of rank $r = 2$ to the standard Whittle approximation increases the accuracy from $3$ to $14$ digits for a matrix $\mathbf{\Sigma} \in \mathbb{R}^{10^5 \times 10^5}$. The method and analysis of this work applies well beyond time series analysis, providing an algorithm for extremely accurate direct solves with a wide variety of symmetric Toeplitz matrices. The analysis employed here largely depends on asymptotic expansions of oscillatory integrals, and also provides a new perspective on when existing spectral-domain approximation methods for Gaussian log-likelihoods can be particularly problematic.
FPGAs are rarely mentioned when discussing the implementation of large machine learning applications, such as Large Language Models (LLMs), in the data center. There has been much evidence showing that single FPGAs can be competitive with GPUs in performance for some computations, especially for low latency, and often much more efficient when power is considered. This suggests that there is merit to exploring the use of multiple FPGAs for large machine learning applications. The challenge with using multiple FPGAs is that there is no commonly-accepted flow for developing and deploying multi-FPGA applications, i.e., there are no tools to describe a large application, map it to multiple FPGAs and then deploy the application on a multi-FPGA platform. In this paper, we explore the feasibility of implementing large transformers using multiple FPGAs by developing a scalable multi-FPGA platform and some tools to map large applications to the platform. We validate our approach by designing an efficient multi-FPGA version of the I-BERT transformer and implement one encoder using six FPGAs as a working proof-of-concept to show that our platform and tools work. Based on our proof-of-concept prototype and the estimations of performance using the latest FPGAs compared to GPUs, we conclude that there can be a place for FPGAs in the world of large machine learning applications. We demonstrate a promising first step that shows that with the right infrastructure and tools it is reasonable to continue to explore the possible benefits of using FPGAs for applications such as LLMs.
Vulnerability detection is crucial for ensuring the security and reliability of software systems. Recently, Graph Neural Networks (GNNs) have emerged as a prominent code embedding approach for vulnerability detection, owing to their ability to capture the underlying semantic structure of source code. However, GNNs face significant challenges in explainability due to their inherently black-box nature. To this end, several factual reasoning-based explainers have been proposed. These explainers provide explanations for the predictions made by GNNs by analyzing the key features that contribute to the outcomes. We argue that these factual reasoning-based explanations cannot answer critical what-if questions: What would happen to the GNN's decision if we were to alter the code graph into alternative structures? Inspired by advancements of counterfactual reasoning in artificial intelligence, we propose CFExplainer, a novel counterfactual explainer for GNN-based vulnerability detection. Unlike factual reasoning-based explainers, CFExplainer seeks the minimal perturbation to the input code graph that leads to a change in the prediction, thereby addressing the what-if questions for vulnerability detection. We term this perturbation a counterfactual explanation, which can pinpoint the root causes of the detected vulnerability and furnish valuable insights for developers to undertake appropriate actions for fixing the vulnerability. Extensive experiments on four GNN-based vulnerability detection models demonstrate the effectiveness of CFExplainer over existing state-of-the-art factual reasoning-based explainers.
Text Classification is the most essential and fundamental problem in Natural Language Processing. While numerous recent text classification models applied the sequential deep learning technique, graph neural network-based models can directly deal with complex structured text data and exploit global information. Many real text classification applications can be naturally cast into a graph, which captures words, documents, and corpus global features. In this survey, we bring the coverage of methods up to 2023, including corpus-level and document-level graph neural networks. We discuss each of these methods in detail, dealing with the graph construction mechanisms and the graph-based learning process. As well as the technological survey, we look at issues behind and future directions addressed in text classification using graph neural networks. We also cover datasets, evaluation metrics, and experiment design and present a summary of published performance on the publicly available benchmarks. Note that we present a comprehensive comparison between different techniques and identify the pros and cons of various evaluation metrics in this survey.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191