Search

The 3rd Workshop on Maritime Computer Vision (MaCVi) 2025 addresses maritime computer vision for Unmanned Surface Vehicles (USV) and underwater. This report offers a comprehensive overview of the findings from the challenges. We provide both statistical and qualitative analyses, evaluating trends from over 700 submissions. All datasets, evaluation code, and the leaderboard are available to the public at https://macvi.org/workshop/macvi25., Comment: Part of the MaCVi 2025 workshop

The emergence of Large Language Models (LLMs) has necessitated the adoption of parallel training techniques, involving the deployment of thousands of GPUs to train a single model. Unfortunately, we have found that the efficiency of current parallel training is often suboptimal, largely due to the following two main issues. Firstly, hardware failures are inevitable, leading to interruptions in the training tasks. The inability to quickly identify the faulty components results in a substantial waste of GPU resources. Secondly, since GPUs must wait for parameter synchronization to complete before proceeding to the next round of computation, network congestions can greatly increase the waiting time for GPUs. To address these challenges, this paper introduces a communication-driven solution, namely the C4. The key insights of C4 are two folds. First, in parallel training, collective communication exhibits periodic and homogeneous characteristics, so any anomalies are certainly due to some form of hardware malfunction. By leveraging this feature, C4 can rapidly identify the faulty components, swiftly isolate the anomaly, and restart the task, thereby avoiding resource wastage caused by delays in anomaly detection. Second, the predictable communication model of collective communication, involving few large flows, allows C4 to efficiently execute traffic planning, substantially reducing network congestion. C4 has been extensively implemented across our production systems, cutting error-induced overhead by roughly 30% and enhancing runtime performance by about 15% for certain applications with moderate communication costs.

The semantic segmentation of pelvic organs via MRI has important clinical significance. Recently, deep learning-enabled semantic segmentation has facilitated the three-dimensional geometric reconstruction of pelvic floor organs, providing clinicians with accurate and intuitive diagnostic results. However, the task of labeling pelvic floor MRI segmentation, typically performed by clinicians, is labor-intensive and costly, leading to a scarcity of labels. Insufficient segmentation labels limit the precise segmentation and reconstruction of pelvic floor organs. To address these issues, we propose a semi-supervised framework for pelvic organ segmentation. The implementation of this framework comprises two stages. In the first stage, it performs self-supervised pre-training using image restoration tasks. Subsequently, fine-tuning of the self-supervised model is performed, using labeled data to train the segmentation model. In the second stage, the self-supervised segmentation model is used to generate pseudo labels for unlabeled data. Ultimately, both labeled and unlabeled data are utilized in semi-supervised training. Upon evaluation, our method significantly enhances the performance in the semantic segmentation and geometric reconstruction of pelvic organs, Dice coefficient can increase by 2.65% averagely. Especially for organs that are difficult to segment, such as the uterus, the accuracy of semantic segmentation can be improved by up to 3.70%.

Quantum power flow (QPF) provides inspiring directions for tackling power flow's computational burdens leveraging quantum computing. However, existing QPF methods are mainly based on noise-sensitive quantum algorithms, whose practical utilization is significantly hindered by the limited capability of today's noisy-intermediate-scale quantum (NISQ) devices. This paper devises a NISQ-QPF algorithm, which enables power flow calculation on noisy quantum computers. The main contributions include: (1) a variational quantum circuit (VQC)-based AC power flow formulation, which enables QPF using short-depth quantum circuits; (2) noise-resilient QPF solvers based on the variational quantum linear solver (VQLS) and modified fast decoupled power flow; (3) a practical NISQ-QPF framework for implementable and reliable power flow analysis on noisy quantum machines. Promising case studies validate the effectiveness and accuracy of NISQ-QPF on IBM's real, noisy quantum devices., Comment: 6 pages, 6 figures

We devise neuro-dynamic state estimation (Neuro-DSE), a learning-based dynamic state estimation (DSE) algorithm for networked microgrids (NMs) under unknown subsystems. Our contributions include: 1) a data-driven Neuro-DSE algorithm for NMs DSE with partially unidentified dynamic models, which incorporates the neural-ordinary-differential-equations (ODE-Net) into Kalman filters; 2) a self-refining Neuro-DSE algorithm (Neuro-DSE+) which enables data-driven DSE under limited and noisy measurements by establishing an automatic filtering, augmenting and correcting framework; 3) a Neuro-KalmanNet-DSE algorithm which further integrates KalmanNet with Neuro-DSE to relieve the model mismatch of both neural- and physics-based dynamic models; and 4) an augmented Neuro-DSE for joint estimation of NMs states and unknown parameters (e.g., inertia). Extensive case studies demonstrate the efficacy of Neuro-DSE and its variants under different noise levels, control modes, power sources, observabilities and model knowledge, respectively., Comment: This paper needs to be withdrawn by the author. In Section II, Part C, there is lack of procedure to achieve parameter estimation using the proposed model. In Section V, Part E, experiment parameter setting is missed. Noise for estimating inertia case needs to be reset for simulation. Additional tests need to be added. These two parts need to be rewritten

Acoustic-resolution photoacoustic microscopy (AR-PAM) is a promising tool for microvascular imaging. In the focal region, resolution of AR-PAM is determined by the ultrasound transducer and ultimately limited by acoustic diffraction. In the out-of-focus region, resolution deteriorates with increasing distance from the focal plane, which restricts depth of focus (DOF). Besides, a trade-off exists between resolution and DOF. Previously, synthetic aperture focusing technique (SAFT) and/or deconvolution methods have been demonstrated to enhance AR-PAM images. However, they suffer from issues in low resolution, low signal-to-noise ratio (SNR), and/or poor image fidelity. Here, we propose a novel algorithm for AR-PAM to enhance image resolution, SNR, and fidelity. The algorithm consists of a Fourier accumulation SAFT (FA-SAFT) and a directional model-based (D-MB) deconvolution method. Inspired from Fourier denoising technique and directional SAFT, FA-SAFT mainly compensates for the defocusing effect. Besides, D-MB deconvolution enhances the resolution as well as preserves the image fidelity, especially for the objects with line patterns such as microvasculature. Full width at half maximum of 26-31 um over DOF of 1.8 mm and minimum resolvable distance of 46-49 um are experimentally achieved by imaging tungsten wire phantom. Moreover, imaging of leaf skeleton phantom and in vivo imaging of mouse blood vessels also prove that our algorithm is capable of providing high-resolution, high-SNR, and good-fidelity results for complex structures and for in vivo applications., Comment: 34 pages (including 16 pages of supplementary materials)

This letter is a proof of concept for quantum power flow (QPF) algorithms which underpin various unprecedentedly efficient power system analytics exploiting quantum computing. Our contributions are three-fold: 1) Establish a quantum-state-based fast decoupled model empowered by Hermitian and constant Jacobian matrices; 2) Devise an enhanced Harrow-Hassidim-Lloyd (HHL) algorithm to solve the fast decoupled QPF; 3) Further improve the HHL efficiency by parameterizing quantum phase estimation and reciprocal rotation only at the beginning stage. Promising test results validate the accuracy and efficacy of QPF and demonstrate QPF's enormous potential in the era of quantum computing.

Policy optimization methods remain a powerful workhorse in empirical Reinforcement Learning (RL), with a focus on neural policies that can easily reason over complex and continuous state and/or action spaces. Theoretical understanding of strategic exploration in policy-based methods with non-linear function approximation, however, is largely missing. In this paper, we address this question by designing ENIAC, an actor-critic method that allows non-linear function approximation in the critic. We show that under certain assumptions, e.g., a bounded eluder dimension $d$ for the critic class, the learner finds a near-optimal policy in $O(\poly(d))$ exploration rounds. The method is robust to model misspecification and strictly extends existing works on linear function approximation. We also develop some computational optimizations of our approach with slightly worse statistical guarantees and an empirical adaptation building on existing deep RL tools. We empirically evaluate this adaptation and show that it outperforms prior heuristics inspired by linear methods, establishing the value via correctly reasoning about the agent's uncertainty under non-linear function approximation.

Motivated by the prevailing paradigm of using unsupervised learning for efficient exploration in reinforcement learning (RL) problems [tang2017exploration,bellemare2016unifying], we investigate when this paradigm is provably efficient. We study episodic Markov decision processes with rich observations generated from a small number of latent states. We present a general algorithmic framework that is built upon two components: an unsupervised learning algorithm and a no-regret tabular RL algorithm. Theoretically, we prove that as long as the unsupervised learning algorithm enjoys a polynomial sample complexity guarantee, we can find a near-optimal policy with sample complexity polynomial in the number of latent states, which is significantly smaller than the number of observations. Empirically, we instantiate our framework on a class of hard exploration problems to demonstrate the practicality of our theory.

An enhanced microgrid power flow (EMPF) is devised to incorporate hierarchical control effects. The new contributions are threefold: 1) an advanced-hierarchical-control-based Newton approach is established to accurately assess power sharing and voltage regulation effects; 2) a modified Jacobian matrix is derived to incorporate droop control and various secondary control modes; and 3) the secondary adjustment is calculated on top of the droop-control-based power flow results to ensure a robust Newton solution. Case studies validate that EMPF is efficacious and efficient and can serve as a powerful tool for microgrid operation and monitoring, especially for those highly meshed microgrids in urban areas., Comment: 4 pages,3 figures,letter

The Discriminative Correlation Filter (CF) uses a circulant convolution operation to provide several training samples for the design of a classifier that can distinguish the target from the background. The filter design may be interfered by objects close to the target during the tracking process, resulting in tracking failure. This paper proposes an adaptive distraction context aware tracking algorithm to solve this problem. In the response map obtained for the previous frame by the CF algorithm, we adaptively find the image blocks that are similar to the target and use them as negative samples. This diminishes the influence of similar image blocks on the classifier in the tracking process and its accuracy is improved. The tracking results on video sequences show that the algorithm can cope with rapid changes such as occlusion and rotation, and can adaptively use the distractive objects around the target as negative samples to improve the accuracy of target tracking.

One of the key approaches to save samples in reinforcement learning (RL) is to use knowledge from an approximate model such as its simulator. However, how much does an approximate model help to learn a near-optimal policy of the true unknown model? Despite numerous empirical studies of transfer reinforcement learning, an answer to this question is still elusive. In this paper, we study the sample complexity of RL while an approximate model of the environment is provided. For an unknown Markov decision process (MDP), we show that the approximate model can effectively reduce the complexity by eliminating sub-optimal actions from the policy searching space. In particular, we provide an algorithm that uses $\widetilde{O}(N/(1-\gamma)^3/\varepsilon^2)$ samples in a generative model to learn an $\varepsilon$-optimal policy, where $\gamma$ is the discount factor and $N$ is the number of near-optimal actions in the approximate model. This can be much smaller than the learning-from-scratch complexity $\widetilde{\Theta}(SA/(1-\gamma)^3/\varepsilon^2)$, where $S$ and $A$ are the sizes of state and action spaces respectively. We also provide a lower bound showing that the above upper bound is nearly-tight if the value gap between near-optimal actions and sub-optimal actions in the approximate model is sufficiently large. Our results provide a very precise characterization of how an approximate model helps reinforcement learning when no additional assumption on the model is posed.

Cardiac structure segmentation plays an important role in medical analysis procedures. Images' blurred boundaries issue always limits the segmentation performance. To address this difficult problem, we presented a novel network structure which embedded dilated pyramid pooling block in the skip connections between networks' encoding and decoding stage. A dilated pyramid pooling block is made up of convolutions and pooling operations with different vision scopes. Equipped the model with such module, it could be endowed with multi-scales vision ability. Together combining with other techniques, it included a multi-scales initial features extraction and a multi-resolutions' prediction aggregation module. As for backbone feature extraction network, we referred to the basic idea of Xception network which benefited from separable convolutions. Evaluated on the Post 2017 MICCAI-ACDC challenge phase data, our proposed model could achieve state-of-the-art performance in left ventricle (LVC) cavities and right ventricle cavities (RVC) segmentation tasks. Results revealed that our method has advantages on both geometrical (Dice coefficient, Hausdorff distance) and clinical evaluation (Ejection Fraction, Volume), which represent closer boundaries and more statistically significant separately.

Empirical risk minimization is an important class of optimization problems with many popular machine learning applications, and stochastic variance reduction methods are popular choices for solving them. Among these methods, SVRG and Katyusha X (a Nesterov accelerated SVRG) achieve fast convergence without substantial memory requirement. In this paper, we propose to accelerate these two algorithms by \textit{inexact preconditioning}, the proposed methods employ \textit{fixed} preconditioners, although the subproblem in each epoch becomes harder, it suffices to apply \textit{fixed} number of simple subroutines to solve it inexactly, without losing the overall convergence. As a result, this inexact preconditioning strategy gives provably better iteration complexity and gradient complexity over SVRG and Katyusha X. We also allow each function in the finite sum to be nonconvex while the sum is strongly convex. In our numerical experiments, we observe an on average $8\times$ speedup on the number of iterations and $7\times$ speedup on runtime.

In this paper, we propose AsyncQVI, an asynchronous-parallel Q-value iteration for discounted Markov decision processes whose transition and reward can only be sampled through a generative model. Given such a problem with $|\mathcal{S}|$ states, $|\mathcal{A}|$ actions, and a discounted factor $\gamma\in(0,1)$, AsyncQVI uses memory of size $\mathcal{O}(|\mathcal{S}|)$ and returns an $\varepsilon$-optimal policy with probability at least $1-\delta$ using $$\tilde{\mathcal{O}}\big(\frac{|\mathcal{S}||\mathcal{A}|}{(1-\gamma)^5\varepsilon^2}\log(\frac{1}{\delta})\big)$$ samples. AsyncQVI is also the first asynchronous-parallel algorithm for discounted Markov decision processes that has a sample complexity, which nearly matches the theoretical lower bound. The relatively low memory footprint and parallel ability make AsyncQVI suitable for large-scale applications. In numerical tests, we compare AsyncQVI with four sample-based value iteration methods. The results show that our algorithm is highly efficient and achieves linear parallel speedup., Comment: Accepted by AISTATS 2020

In this paper, we propose the Asynchronous Accelerated Nonuniform Randomized Block Coordinate Descent algorithm (A2BCD), the first asynchronous Nesterov-accelerated algorithm that achieves optimal complexity. This parallel algorithm solves the unconstrained convex minimization problem, using p computing nodes which compute updates to shared solution vectors, in an asynchronous fashion with no central coordination. Nodes in asynchronous algorithms do not wait for updates from other nodes before starting a new iteration, but simply compute updates using the most recent solution information available. This allows them to complete iterations much faster than traditional ones, especially at scale, by eliminating the costly synchronization penalty of traditional algorithms. We first prove that A2BCD converges linearly to a solution with a fast accelerated rate that matches the recently proposed NU_ACDM, so long as the maximum delay is not too large. Somewhat surprisingly, A2BCD pays no complexity penalty for using outdated information. We then prove lower complexity bounds for randomized coordinate descent methods, which show that A2BCD (and hence NU_ACDM) has optimal complexity to within a constant factor. We confirm with numerical experiments that A2BCD outperforms NU_ACDM, which is the current fastest coordinate descent algorithm, even at small scale. We also derive and analyze a second-order ordinary differential equation, which is the continuous-time limit of our algorithm, and prove it converges linearly to a solution with a similar accelerated rate., Comment: 33 pages, 6 figures

We present new quasars discovered in the vicinity of the Andromeda and Triangulum galaxies with the LAMOST during the 2010 and 2011 observational seasons. Quasar candidates are selected based on the available SDSS, KPNO 4 m telescope, XSTPS optical, and WISE near infrared photometric data. We present 509 new quasars discovered in a stripe of ~135 sq. deg from M31 to M33 along the Giant Stellar Stream in the 2011 pilot survey datasets, and also 17 new quasars discovered in an area of ~100 sq. deg that covers the central region and the southeastern halo of M31 in the 2010 commissioning datasets. These 526 new quasars have i magnitudes ranging from 15.5 to 20.0, redshifts from 0.1 to 3.2. They represent a significant increase of the number of identified quasars in the vicinity of M31 and M33. There are now 26, 62 and 139 known quasars in this region of the sky with i magnitudes brighter than 17.0, 17.5 and 18.0 respectively, of which 5, 20 and 75 are newly-discovered. These bright quasars provide an invaluable collection with which to probe the kinematics and chemistry of the ISM/IGM in the Local Group of galaxies. A total of 93 quasars are now known with locations within 2.5 deg of M31, of which 73 are newly discovered. Tens of quasars are now known to be located behind the Giant Stellar Stream, and hundreds behind the extended halo and its associated substructures of M31. The much enlarged sample of known quasars in the vicinity of M31 and M33 can potentially be utilized to construct a perfect astrometric reference frame to measure the minute PMs of M31 and M33, along with the PMs of substructures associated with the Local Group of galaxies. Those PMs are some of the most fundamental properties of the Local Group., Comment: 26 pages, 6 figures, AJ accepted