检索结果-内蒙古大学图书馆

TOPOGRAPH: AN EFFICIENT GRAPH-BASED FRAMEWORK FOR STRICTLY TOPOLOGY PRESERVING IMAGE SEGMENTATION

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lux, Laurin Berger, Alexander H. Weers, Alexander Stucki, Nico Rueckert, Daniel Bauer, Ulrich Paetzold, Johannes C. School of Computation Information and Technology Technical University of Munich Germany Department of Computing Imperial College London United Kingdom Munich Center for Machine Learning Germany Munich Data Science Institute Technical University of Munich Munich Germany

Topological correctness plays a critical role in many image segmentation tasks, yet most networks are trained using pixel-wise loss functions, such as Dice, neglecting topological accuracy. Existing topology-aware methods often lack robust topological guarantees, are limited to specific use cases, or impose high computational costs. In this work, we propose a novel, graph-based framework for topologically accurate image segmentation that is both computationally efficient and generally applicable. Our method constructs a component graph that fully encodes the topological information of both the prediction and ground truth, allowing us to efficiently identify topologically critical regions and aggregate a loss based on local neighborhood information. Furthermore, we introduce a strict topological metric capturing the homotopy equivalence between the union and intersection of prediction-label pairs. We formally prove the topological guarantees of our approach and empirically validate its effectiveness on binary and multi-class datasets. Our loss demonstrates state-of-the-art performance with up to fivefold faster loss computation compared to persistent homology methods. © 2024, CC BY.

关键词： Image segmentation

ECTSum: A New Benchmark dataset For Bullet Point Summarization of Long Earnings Call Transcripts

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mukherjee, Rajdeep Bohra, Abhinav Banerjee, Akash Sharma, Soumya Hegde, Manjunath Shaikh, Afreen Shrivastava, Shivani Dasgupta, Koustuv Ganguly, Niloy Ghosh, Saptarshi Goyal, Pawan Department of Computer Science and Engineering IIT Kharagpur India Goldman Sachs Data Science and Machine Learning Group India Leibniz University of Hannover Germany

Despite tremendous progress in automatic summarization, state-of-the-art methods are predominantly trained to excel in summarizing short newswire articles, or documents with strong layout biases such as scientific articles or govt reports. Efficient techniques to summarize financial documents, including facts and figures, have largely been unexplored, majorly due to the unavailability of suitable datasets. Here, we present ECTSum, a new dataset with transcripts of earnings calls (ECTs), hosted by public companies, as documents, and short experts-written telegram-style bullet point summaries derived from corresponding Reuters articles. ECTs are long unstructured documents without any prescribed length limit or format. We benchmark ECTSum with state-of-the-art summarizers across various metrics evaluating the content quality and factual consistency of the generated summaries. Finally, we present a simple-yet-effective approach, ECT-BPS, to generate a set of bullet points that precisely capture the important facts discussed in the calls. Copyright © 2022, The Authors. All rights reserved.

关键词： Benchmarking

Partial counterfactual identification and uplift modeling: theoretical results and real-world assessment

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Verhelst, Théo Mercier, Denis Shrestha, Jeevan Bontempi, Gianluca Machine Learning Group Department of Computer Science Université Libre de Bruxelles Brussels Belgium Data Science Team Orange Belgium Brussels Belgium

Counterfactuals are central in causal human reasoning and the scientific discovery process. The uplift, also called conditional average treatment effect, measures the causal effect of some action, or treatment, on the outcome of an individual. This paper discusses how it is possible to derive bounds on the probability of counterfactual statements based on uplift terms. First, we derive some original bounds on the probability of counterfactuals and we show that tightness of such bounds depends on the information of the feature set on the uplift term. Then, we propose a point estimator based on the assumption of conditional independence between the counterfactual outcomes. The quality of the bounds and the point estimators are assessed on synthetic data and a large real-world customer data set provided by a telecom company, showing significant improvement over the state of the art. © 2022, CC BY-NC-ND.

关键词：

Unleashing WSN Potential: Bowerbird Optimized Energy-Conscious Multipath Clustering with Causal Dilated Cosine for Enhanced Load Balancing 4

学校读者我要写书评

暂无评论

Unleashing WSN Potential: Bowerbird Optimized Energy-Conscio...

4th International Conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Joon, Rakesh Kumar Anitha, R. Selvan, Saravana Latha Mageshwari, P.S. Gayathri Priya, S. Malathi, K. Ganga Institute of Technology and Management Department of Electronics and Communication Engineering Haryana Kablana124104 India S.A. Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu Chennai600077 India School of Professional Engineering Manukau Institute of Technology Auckland2104 New Zealand Tamil Nadu Kavaraipettai601206 India R.M.D. Engineering College Department of Electronics and Communication Engineering Tamil Nadu Kavaraipettai601206 India Saveetha Engineering College Department of Artificial Intelligence and Machine Learning Tamil Nadu Chennai602105 India

ISBN: (纸本)9798331523923

Wireless Sensor Networks (WSNs) are essential in the collection of real time data across different fields, including environmental monitoring and process control. However, due to the bounded amount of energy in sensor nodes, network lifetime becomes an issue, which hinders performance and reliability. Thus, optimization of WSN performance in an attempt to minimize energy consumption is essential for reliable data transmission. In conventional routing and clustering models, network load distribution is not achieved adequately, resulting in a more significant loading of nodes and faster exhaustion of energy. To solve these problems, it is necessary to carefully design load distribution and path finding algorithms to support long-term WSN operation. The objective of this research is to design a framework-Ski-CDiCo-BO-that integrates Skill Optimization for clustering, and ensuring an energy-efficient paths while reducing redundant transmissions on nodes and conserving node energies, and uses the Causal Dilated Cosine Architecture for sophisticated load balancing, and Bowerbird Optimization for improving the parameterization of neural networks. Analysis reveals that the presented Ski-CDiCo-BO framework provides improved performance of various parameters including data delivery success rate of above 99.8% and network lifetime gain by up to 99.5%. Also, load distribution accuracy remains above 99.3%, which indicates that the framework is capable of avoiding node overload and end-to-end delay improved upon by 99.6%, indicating that the solution maintains high parameters even in dynamically changing conditions. In conclusion, Ski-CDiCo-BO maximizes WSN efficiency by implementing cutting-edge clustering, load balancing, and optimization techniques, setting new standards for energy-conscious and reliable sensor network performance across diverse applications. © 2025 IEEE.

关键词： Sensor nodes

Quantization of Bandlimited Graph Signals

学校读者我要写书评

暂无评论

Quantization of Bandlimited Graph Signals

International Conference on Sampling Theory and Applications (SampTA)

作者： Felix Krahmer He Lyu Rayan Saab Anna Veselovska Rongrong Wang Department of Mathematics & Munich Data Science Institute Technical University of Munich and Munich Center for Machine Learning Garching/Munich Germany Department of Mathematics & Halicioglu Data Science Institute University of California San Diego San Diego USA Department of Computational Mathematics Science and Engineering & Department of Mathematics Michigan State University East Lansing USA

Graph models and graph-based signals are becoming increasingly important in machine learning, natural sciences, and modern signal processing. In this paper, we address the problem of quantizing bandlimited graph signals. We introduce two classes of noise-shaping algorithms for graph signals that differ in their sampling methodologies. We demonstrate that these algorithms can be efficiently used to construct quantized representatives of bandlimited graph-based signals with bounded amplitude. Moreover, for one of the algorithms, we provide theoretical guarantees on the relative error between the quantized representative and the true signal.

关键词：

XpertAI: uncovering model strategies for sub-manifolds

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Letzgus, Simon Müller, Klaus-Robert Montavon, Grégoire Machine Learning Group Technische Universität Berlin Germany BIFOLD Berlin Institute for the Foundations of Learning and Data Berlin Germany Department of Artificial Intelligence Korea University Seoul Korea Republic of Max Planck Institute for Informatics Saarbrücken Germany Department of Mathematics and Computer Science Freie Universität Berlin Germany

In recent years, Explainable AI (XAI) methods have facilitated profound validation and knowledge extraction from ML models. While extensively studied for classification, few XAI solutions have addressed the challenges specific to regression models. In regression, explanations need to be precisely formulated to address specific user queries (e.g. distinguishing between ‘why is the output above 0?’ and ‘why is the output above 50?’). They should furthermore reflect the model’s behavior on the relevant data sub-manifold. In this paper, we introduce XpertAI, a framework that disentangles the prediction strategy into multiple range-specific sub-strategies and allows formulating precise queries about the model (the ‘explanandum’) as a linear combination of those sub-strategies. XpertAI is formulated generally to work alongside popular XAI attribution techniques, based on occlusion, gradient integration, or reverse propagation. Qualitative and quantitative results, demonstrate the benefits of our approach. © 2024, CC BY.

关键词： Regression analysis

Modeling lens potentials with continuous neural fields in galaxy-scale strong lenses

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Biggio, Luca Vernardos, Georgios Galan, Aymeric Peel, Austin Data Analytics Lab Institute of Machine Learning Department of Computer Science ETHZ Switzerland Observatoire de Sauverny Versoix1290 Switzerland

Strong gravitational lensing is a unique observational tool for studying the dark and luminous mass distribution both within and between galaxies. Given the presence of substructures, current strong lensing observations demand more complex mass models than smooth analytical profiles, such as power-law ellipsoids. In this work, we introduce a continuous neural field to predict the lensing potential at any position throughout the image plane, allowing for a nearly model-independent description of the lensing mass. We apply our method on simulated Hubble Space Telescope imaging data containing different types of perturbations to a smooth mass distribution: a localized dark subhalo, a population of subhalos, and an external shear perturbation. Assuming knowledge of the source surface brightness, we use the continuous neural field to model either the perturbations alone or the full lensing potential. In both cases, the resulting model is able to fit the imaging data, and we are able to accurately recover the properties of both the smooth potential and of the perturbations. Unlike many other deep learning methods, ours explicitly retains lensing physics (i.e., the lens equation) and introduces high flexibility in the model only where required, namely, in the lens potential. Moreover, the neural network does not require pre-training on large sets of labelled data and predicts the potential from the single observed lensing image. Our model is implemented in the fully differentiable lens modeling code Herculens. © 2022, CC BY.

关键词： Gravitation

Enhancing Interpretability: The Role of Explainable AI in Healthcare Diagnostics

学校读者我要写书评

暂无评论

Enhancing Interpretability: The Role of Explainable AI in He...

Electronics and Renewable Systems (ICEARS), International Conference on

作者： Nikita Zade Meher Langote Prateek Verma Department of Artificial Intelligence & Data Science Faculty of Engineering & Technology Datta Meghe Institute of Higher Education (DU) Sawangi Maharashtra India Department of Artificial Intelligence & Machine Learning Faculty of Engineering & Technology Datta Meghe Institute of Higher Education (DU) Sawangi Maharashtra India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

XAI is now transforming the use of AI in diagnosing diseases by overcoming some of the problems inherent in most black-box approaches. In time-sensitive speciality areas like computer-aided diagnosis, image analysis, and predictive modelling, SHAP, LIME, and attention-based XAI techniques explain how AI decides to help doctors and other healthcare professionals trust AI. Therefore, this paper aims to clarify why XAI is needed in healthcare, introduce techniques, and show their examples in cancer diagnosis and disease prognosis. XAI improves diagnostic performance and satisfies regulatory and ethical requirements for increased usage in clinical practice. Because of XAI, clinicians can use the best of artificial intelligence to complement their knowledge in enhancing the treatment of patients. That is why the outlook of XAI in healthcare includes the next steps in achieving higher scalability, managing bias, and working with diverse regulatory frameworks, which will define the future of AI solutions in healthcare.

关键词： Renewable energy sources Explainable AI Scalability Closed box Medical services Predictive models Regulation Artificial intelligence Prognostics and health management Cancer

Instance-Dependent Noisy Label learning via Graphical Modelling

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Garg, Arpit Nguyen, Cuong Felix, Rafael Do, Thanh-Toan Carneiro, Gustavo Australian Institute for Machine Learning University of Adelaide Australia Department of Data Science and AI Faculty of Information Technology Monash University Australia

Noisy labels are unavoidable yet troublesome in the ecosystem of deep learning because models can easily overfit them. There are many types of label noise, such as symmetric, asymmetric and instance-dependent noise (IDN), with IDN being the only type that depends on image information. Such dependence on image information makes IDN a critical type of label noise to study, given that la-belling mistakes are caused in large part by insufficient or ambiguous information about the visual classes present in images. Aiming to provide an effective technique to address IDN, we present a new graphical modelling approach called InstanceGM, that combines discriminative and generative models. The main contributions of InstanceGM are: i) the use of the continuous Bernoulli distribution to train the generative model, offering significant training advantages, and ii) the exploration of a state-of-the-art noisy-label discriminative classifier to generate clean labels from instance-dependent noisy-label samples. InstanceGM is competitive with current noisy-label learning approaches, particularly in IDN benchmarks using synthetic and real-world datasets, where our method shows better accuracy than the competitors in most experiments. © 2022, CC BY.

关键词： Deep learning