检索结果-内蒙古大学图书馆

A Two-Stage Minimum Cost Multicut Approach to Self-supervised Multiple Person Tracking 15th

学校读者我要写书评

暂无评论

A Two-Stage Minimum Cost Multicut Approach to Self-supervise...

15th Asian Conference on Computer Vision, ACCV 2020

作者： Ho, Kalun Kardoost, Amirhossein Pfreundt, Franz-Josef Keuper, Janis Keuper, Margret Fraunhofer Center Machine Learning Sankt Augustin Germany CC-HPC Fraunhofer ITWM Kaiserslautern Germany Data and Web Science Group University of Mannheim Mannheim Germany Institute for Machine Learning and Analytics Offenburg University Offenburg Germany

ISBN: (纸本)9783030695316

Multiple Object Tracking (MOT) is a long-standing task in computer vision. Current approaches based on the tracking by detection paradigm either require some sort of domain knowledge or supervision to associate data correctly into tracks. In this work, we present a self-supervised multiple object tracking approach based on visual features and minimum cost lifted multicuts. Our method is based on straight-forward spatio-temporal cues that can be extracted from neighboring frames in an image sequences without supervision. Clustering based on these cues enables us to learn the required appearance invariances for the tracking task at hand and train an AutoEncoder to generate suitable latent representations. Thus, the resulting latent representations can serve as robust appearance cues for tracking even over large temporal distances where no reliable spatio-temporal features can be extracted. We show that, despite being trained without using the provided annotations, our model provides competitive results on the challenging MOT Benchmark for pedestrian tracking. © 2021, Springer Nature Switzerland AG.

关键词： Computer vision

Optimal bounds for ℓp sensitivity sampling via ℓ2 augmentation 24

学校读者我要写书评

暂无评论

Optimal bounds for ℓp sensitivity sampling via ℓ2 augmenta...

Proceedings of the 41st International Conference on machine learning

作者： Alexander Munteanu Simon Omlor Dortmund Data Science Center Faculties of Statistics and Computer Science TU Dortmund University Dortmund Germany Faculty of Statistics TU Dortmund University Dortmund Germany and Lamarr-Institute for Machine Learning and Artificial Intelligence Dortmund Germany

data subsampling is one of the most natural methods to approximate a massively large data set by a small representative proxy. In particular, sensitivity sampling received a lot of attention, which samples points proportional to an individual importance measure called sensitivity. This framework reduces in very general settings the size of data to roughly the VC dimension d times the total sensitivity S while providing strong (1±ε) guarantees on the quality of approximation. The recent work of Woodruff & Yasuda (2023c) improved substantially over the general $\tilde O(\varepsilon^{-2}\mathfrak Sd)$ bound for the important problem of ℓp subspace embeddings to $\tilde O(\varepsilon^{-2}\mathfrak S^{2/p})$ for p ∈ [1, 2]. Their result was subsumed by an earlier $\tilde O(\varepsilon^{-2}\mathfrak Sd^{1-p/2})$ bound which was implicitly given in the work of Chen & Derezinski (2021). We show that their result is tight when sampling according to plain ℓp sensitivities. We observe that by augmenting the ℓp sensitivities by ℓ2 sensitivities, we obtain better bounds improving over the aforementioned results to optimal linear $\tilde O(\varepsilon^{-2}(\mathfrak S+d)) = \tilde O(\varepsilon^{-2}d)$ sampling complexity for all p ∈ [1, 2]. In particular, this resolves an open question of Woodruff & Yasuda (2023c) in the affirmative for p ∈ [1, 2] and brings sensitivity subsampling into the regime that was previously only known to be possible using Lewis weights (Cohen & Peng, 2015). As an application of our main result, we also obtain an Õ(ε-2µd) sensitivity sampling bound for logistic regression, where µ is a natural complexity measure for this problem. This improves over the previous Õ (ε-2µ2d) bound of Mai et al. (2021) which was based on Lewis weights subsampling.

关键词：

Global High Categorical Resolution Land Cover Mapping via Weak Supervision

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tong, Xin-Yi Dong, Runmin Zhu, Xiao Xiang Chair of Data Science in Earth Observation Technical University of Munich Germany Ministry of Education Key Laboratory for Earth System Modeling Department of Earth System Science Tsinghua University China Munich Center for Machine Learning Germany

Land cover information is indispensable for advancing the United Nations’ sustainable development goals, and land cover mapping under a more detailed category system would significantly contribute to economic livelihood tracking and environmental degradation measurement. However, the substantial difficulty in acquiring fine-grained training data makes the implementation of this task particularly challenging. Here, we propose to combine fully labeled source domain and weakly labeled target domain for weakly supervised domain adaptation (WSDA). This is beneficial as the utilization of sparse and coarse weak labels can considerably alleviate the labor required for precise and detailed land cover annotation. Specifically, we introduce the Prototype-based pseudo-label Rectification and Expansion (PRE) approach, which leverages the prototypes (i.e., the class-wise feature centroids) as the bridge to connect sparse labels and global feature distributions. According to the feature distances to the prototypes, the confidence of pseudo-labels predicted in the unlabeled regions of the target domain is assessed. This confidence is then utilized to guide the dynamic expansion and rectification of pseudo-labels. Based on PRE, we carry out high categorical resolution land cover mapping for 10 cities in different regions around the world, severally using PlanetScope, Gaofen-1, and Sentinel-2 satellite images. In the study areas, we achieve cross-sensor, cross-category, and cross-continent WSDA, with the overall accuracy exceeding 80%. The promising results indicate that PRE is capable of reducing the dependency of land cover classification on high-quality annotations, thereby improving label efficiency. We expect our work to enable global fine-grained land cover mapping, which in turn promote Earth observation to provide more precise and thorough information for environmental monitoring. Copyright © 2024, The Authors. All rights reserved.

关键词： Expansion

Turnstile ℓp leverage score sampling with applications 24

学校读者我要写书评

暂无评论

Turnstile ℓp leverage score sampling with applications

Proceedings of the 41st International Conference on machine learning

The turnstile data stream model offers the most flexible framework where data can be manipulated dynamically, i.e., rows, columns, and even single entries of an input matrix can be added, deleted, or updated multiple times in a data stream. We develop a novel algorithm for sampling rows ai of a matrix A ∈ ℝn×d, proportional to their ℓp norm, when A is presented in a turnstile data stream. Our algorithm not only returns the set of sampled row indexes, it also returns slightly perturbed rows ãi ≈ ai, and approximates their sampling probabilities up to e relative error. When combined with preconditioning techniques, our algorithm extends to ℓp leverage score sampling over turnstile data streams. With these properties in place, it allows us to simulate subsampling constructions of coresets for important regression problems to operate over turnstile data streams with very little overhead compared to their respective off-line subsampling algorithms. For logistic regression, our framework yields the first algorithm that achieves a (1 + ε) approximation and works in a turnstile data stream using polynomial sketch/subsample size, improving over O(1) approximations, or exp(1/ε) sketch size of previous work. We compare experimentally to plain oblivious sketching and plain leverage score sampling algorithms for ℓp and logistic regression.

关键词：

machine-learning Force Fields Reveal Shallow Electronic States on Dynamic Halide Perovskite Surfaces

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Delgado, Frederico P. Simões, Frederico Kronik, Leeor Kaiser, Waldemar Egger, David A. Physics Department TUM School of Natural Sciences Technical University of Munich Germany Department of Molecular Chemistry and Materials Science Weizmann Institute of Science Israel Atomistic Modeling Center Munich Data Science Institute Technical University of Munich Germany Munich Center for Machine Learning Munich Germany

The spectacular performance of halide perovskites in optoelectronic devices is rooted in their favorable tolerance to structural defects. Previous studies showed that defects in these materials generate shallow electronic states that do not degrade device performance. However, how these shallow states persist amid the pronounced thermally-stimulated atomic dynamics on halide perovskite surfaces remains unknown. This work reveals that electronic states at surfaces of the prototypical CsPbBr3 variant are energetically distributed at room temperature, akin to well-passivated inorganic semiconductors, even when covalent bonds remain cleaved and undercoordinated. Specifically, a striking tendency for shallow surface states is found with approximately 70% of surface-state energies appearing within 0.2 eV or ≈8kBT from the valence-band edge. Furthermore, we show that even when surface states appear deeper in the gap, they are not energetically isolated and are less likely to act as traps. We achieve this result by accelerating first-principles calculations via machine-learning techniques and show that the unique atomic dynamics in these materials render the formation of deep electronic states at their surfaces unlikely. These findings reveal the microscopic mechanism behind the low density of deep defect states at dynamic halide perovskite surfaces, which is key to their exceptional performance in devices. © 2025, CC BY.

关键词： Perovskite

GraphMorph: Tubular Structure Extraction by Morphing Predicted Graphs

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Zhao Zhao, Ziwei Wang, Dong Wang, Liwei Center for Data Science Peking University China Yizhun Medical AI Co. Ltd China State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University China Center for Machine Learning Research Peking University China China

Accurately restoring topology is both challenging and crucial in tubular structure extraction tasks, such as blood vessel segmentation and road network extraction. Diverging from traditional approaches based on pixel-level classification, our proposed method, named GraphMorph, focuses on branch-level features of tubular structures to achieve more topologically accurate predictions. GraphMorph comprises two main components: a Graph Decoder and a Morph Module. Utilizing multi-scale features extracted from an image patch by the segmentation network, the Graph Decoder facilitates the learning of branch-level features and generates a graph that accurately represents the tubular structure in this patch. The Morph Module processes two primary inputs: the graph and the centerline probability map, provided by the Graph Decoder and the segmentation network, respectively. Employing a novel SkeletonDijkstra algorithm, the Morph Module produces a centerline mask that aligns with the predicted graph. Furthermore, we observe that employing centerline masks predicted by GraphMorph significantly reduces false positives in the segmentation task, which is achieved by a simple yet effective post-processing strategy. The efficacy of our method in the centerline extraction and segmentation tasks has been substantiated through experimental evaluations across various datasets. Source code will be released soon. Copyright © 2025, The Authors. All rights reserved.

关键词： Image segmentation

Your Transformer May Not be as Powerful as You Expect 36

学校读者我要写书评

暂无评论

Your Transformer May Not be as Powerful as You Expect

36th Conference on Neural Information Processing Systems, NeurIPS 2022

作者： Luo, Shengjie Li, Shanda Zheng, Shuxin Liu, Tie-Yan Wang, Liwei He, Di National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University China Machine Learning Department School of Computer Science Carnegie Mellon University United States Microsoft Research United States Center for Data Science Peking University China Zhejiang Lab China

ISBN: (纸本)9781713871088

Relative Positional Encoding (RPE), which encodes the relative distance between any pair of tokens, is one of the most successful modifications to the original Transformer. As far as we know, theoretical understanding of the RPE-based Transformers is largely unexplored. In this work, we mathematically analyze the power of RPE-based Transformers regarding whether the model is capable of approximating any continuous sequence-to-sequence functions. One may naturally assume the answer is in the affirmative-RPE-based Transformers are universal function approximators. However, we present a negative result by showing there exist continuous sequence-to-sequence functions that RPE-based Transformers cannot approximate no matter how deep and wide the neural network is. One key reason lies in that most RPEs are placed in the softmax attention that always generates a right stochastic matrix. This restricts the network from capturing positional information in the RPEs and limits its capacity. To overcome the problem and make the model more powerful, we first present sufficient conditions for RPE-based Transformers to achieve universal function approximation. With the theoretical guidance, we develop a novel attention module, called Universal RPE-based (URPE) Attention, which satisfies the conditions. Therefore, the corresponding URPE-based Transformers become universal function approximators. Extensive experiments covering typical architectures and tasks demonstrate that our model is parameter-efficient and can achieve superior performance to strong baselines in a wide range of applications. The code will be made publicly available at https://***/lsj2408/URPE. © 2022 Neural information processing systems foundation. All rights reserved.

关键词： Encoding (symbols)

Gradient is All You Need?

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Riedl, Konstantin Klock, Timo Geldhauser, Carina Fornasier, Massimo Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Deeptech Consulting Oslo Norway Munich Data Science Institute Munich Germany

In this paper we provide a novel analytical perspective on the theoretical understanding of gradient-based learning algorithms by interpreting consensus-based optimization (CBO), a recently proposed multi-particle derivative-free optimization method, as a stochastic relaxation of gradient descent. Remarkably, we observe that through communication of the particles, CBO exhibits a stochastic gradient descent (SGD)-like behavior despite solely relying on evaluations of the objective function. The fundamental value of such link between CBO and SGD lies in the fact that CBO is provably globally convergent to global minimizers for ample classes of nonsmooth and nonconvex objective functions, hence, on the one side, offering a novel explanation for the success of stochastic relaxations of gradient descent. On the other side, contrary to the conventional wisdom for which zero-order methods ought to be inefficient or not to possess generalization abilities, our results unveil an intrinsic gradient descent nature of such heuristics. This viewpoint furthermore complements previous insights into the working principles of CBO, which describe the dynamics in the mean-field limit through a nonlinear nonlocal partial differential equation that allows to alleviate complexities of the nonconvex function landscape. Our proofs leverage a completely nonsmooth analysis, which combines a novel quantitative version of the Laplace principle (log-sum-exp trick) and the minimizing movement scheme (proximal iteration). In doing so, we furnish useful and precise insights that explain how stochastic perturbations of gradient descent overcome energy barriers and reach deep levels of nonconvex functions. Instructive numerical illustrations support the provided theoretical insights. Copyright © 2023, The Authors. All rights reserved.

关键词： Optimization

An Improved Finite-time Analysis of Temporal Difference learning with Deep Neural Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ke, Zhifa Wen, Zaiwen Zhang, Junyu Center for Data Science Peking University China Beijing International Center for Mathematical Research Center for Machine Learning Research Changsha Institute for Computing and Digital Economy Beijing China Department of Industrial Systems Engineering and Management National University of Singapore Singapore

Temporal difference (TD) learning algorithms with neural network function parameterization have well-established empirical success in many practical large-scale reinforcement learning tasks. However, theoretical understanding of these algorithms remains challenging due to the nonlinearity of the action-value approximation. In this paper, we develop an improved non-asymptotic analysis of the neural TD method with a general L-layer neural network. New proof techniques are developed and an improved new Õ(ϵ−1) sample complexity is derived. To our best knowledge, this is the first finite-time analysis of neural TD that achieves an Õ(ϵ−1) complexity under the Markovian sampling, as opposed to the best known Õ(ϵ−2) complexity in the existing literature. Copyright © 2024, The Authors. All rights reserved.

关键词： Asymptotic analysis