Search

We introduce a new generative system called Edit Everything, which can take image and text inputs and produce image outputs. Edit Everything allows users to edit images using simple text instructions. Our system designs prompts to guide the visual module in generating requested images. Experiments demonstrate that Edit Everything facilitates the implementation of the visual aspects of Stable Diffusion with the use of Segment Anything model and CLIP. Our system is publicly available at https://github.com/DefengXie/Edit_Everything.

Combining new HI data from a synergetic survey of ASKAP WALLABY and FAST with the ALFALFA data, we study the effect of ram pressure and tidal interactions in the NGC 4636 group. We develop two parameters to quantify and disentangle these two effects on gas stripping in HI-bearing galaxies: the strength of external forces at the optical-disk edge, and the outside-in extents of HI-disk stripping. We find that gas stripping is widespread in this group, affecting 80% of HI-detected non-merging galaxies, and that 41% are experiencing both types of stripping. Among the galaxies experiencing both effects, the two types of strengths are independent, while two HI-stripping extents moderately anticorrelate with each other. Both strengths are correlated with HI-disk shrinkage. The tidal strength is related to a rather uniform reddening of low-mass galaxies ($M_*<10^9\,\text{M}_\odot$) when tidal stripping is the dominating effect. In contrast, ram pressure is not clearly linked to the color-changing patterns of galaxies in the group. Combining these two stripping extents, we estimate the total stripping extent, and put forward an empirical model that can describe the decrease of HI richness as galaxies fall toward the group center. The stripping timescale we derived decreases with distance to the center, from $\mathord{\sim}1\,\text{Gyr}$ beyond $R_{200}$ to $\mathord{\lesssim}10\,\text{Myr}$ near the center. Gas-depletion happens $\mathord{\sim}3\,\text{Gyr}$ since crossing $2R_{200}$ for HI-rich galaxies, but much quicker for HI-poor ones. Our results quantify in a physically motivated way the details and processes of environmental-effects-driven galaxy evolution, and might assist in analyzing hydrodynamic simulations in an observational way., Comment: 44 pages, 22 figures, 5 tables, accepted for publication in ApJ. Tables 4 and 5 are also available in machine-readable form. Values of $f_\text{tid}$ are updated without influencing major results and conclusions

How to ensure fairness is an important topic in federated learning (FL). Recent studies have investigated how to reward clients based on their contribution (collaboration fairness), and how to achieve uniformity of performance across clients (performance fairness). Despite achieving progress on either one, we argue that it is critical to consider them together, in order to engage and motivate more diverse clients joining FL to derive a high-quality global model. In this work, we propose a novel method to optimize both types of fairness simultaneously. Specifically, we propose to estimate client contribution in gradient and data space. In gradient space, we monitor the gradient direction differences of each client with respect to others. And in data space, we measure the prediction error on client data using an auxiliary model. Based on this contribution estimation, we propose a FL method, federated training via contribution estimation (FedCE), i.e., using estimation as global model aggregation weights. We have theoretically analyzed our method and empirically evaluated it on two real-world medical datasets. The effectiveness of our approach has been validated with significant performance improvements, better collaboration fairness, better performance fairness, and comprehensive analytical studies., Comment: Accepted at CVPR 2023

Federated learning is a popular collaborative learning approach that enables clients to train a global model without sharing their local data. Vertical federated learning (VFL) deals with scenarios in which the data on clients have different feature spaces but share some overlapping samples. Existing VFL approaches suffer from high communication costs and cannot deal efficiently with limited overlapping samples commonly seen in the real world. We propose a practical vertical federated learning (VFL) framework called \textbf{one-shot VFL} that can solve the communication bottleneck and the problem of limited overlapping samples simultaneously based on semi-supervised learning. We also propose \textbf{few-shot VFL} to improve the accuracy further with just one more communication round between the server and the clients. In our proposed framework, the clients only need to communicate with the server once or only a few times. We evaluate the proposed VFL framework on both image and tabular datasets. Our methods can improve the accuracy by more than 46.5\% and reduce the communication cost by more than 330$\times$ compared with state-of-the-art VFL methods when evaluated on CIFAR-10. Our code will be made publicly available at \url{https://nvidia.github.io/NVFlare/research/one-shot-vfl}.

This paper studies the leader-following consensuses of uncertain and nonlinear multi-agent systems against composite attacks (CAs), including Denial of Service (DoS) attacks and actuation attacks (AAs). A double-layer control framework is formulated, where a digital twin layer (TL) is added beside the traditional cyber-physical layer (CPL), inspired by the recent Digital Twin technology. Consequently, the resilient control task against CAs can be divided into two parts: One is distributed estimation against DoS attacks on the TL and the other is resilient decentralized tracking control against actuation attacks on the CPL. %The data-driven scheme is used to deal with both model non-linearity and model uncertainty, in which only the input and output data of the system are employed throughout the whole control process. First, a distributed observer based on switching estimation law against DoS is designed on TL. Second, a distributed model free adaptive control (DMFAC) protocol based on attack compensation against AAs is designed on CPL. Moreover, the uniformly ultimately bounded convergence of consensus error of the proposed double-layer DMFAC algorithm is strictly proved. Finally, the simulation verifies the effectiveness of the resilient double-layer control scheme.

We consider Markovian open quantum dynamics (MOQD). We show that, up to small-probability tails, the supports of quantum states evolving under such dynamics propagate with finite speed in any finite-energy subspace. More precisely, we prove that if the initial quantum state is localized in space, then any finite-energy part of the solution of the von Neumann-Lindblad equation is approximately localized inside an energy-dependent light cone. We also obtain an explicit upper bound for the slope of this light cone., Comment: 43 pages

Pause insertion, also known as phrase break prediction and phrasing, is an essential part of TTS systems because proper pauses with natural duration significantly enhance the rhythm and intelligibility of synthetic speech. However, conventional phrasing models ignore various speakers' different styles of inserting silent pauses, which can degrade the performance of the model trained on a multi-speaker speech corpus. To this end, we propose more powerful pause insertion frameworks based on a pre-trained language model. Our approach uses bidirectional encoder representations from transformers (BERT) pre-trained on a large-scale text corpus, injecting speaker embedding to capture various speaker characteristics. We also leverage duration-aware pause insertion for more natural multi-speaker TTS. We develop and evaluate two types of models. The first improves conventional phrasing models on the position prediction of respiratory pauses (RPs), i.e., silent pauses at word transitions without punctuation. It performs speaker-conditioned RP prediction considering contextual information and is used to demonstrate the effect of speaker information on the prediction. The second model is further designed for phoneme-based TTS models and performs duration-aware pause insertion, predicting both RPs and punctuation-indicated pauses (PIPs) that are categorized by duration. The evaluation results show that our models improve the precision and recall of pause insertion and the rhythm of synthetic speech., Comment: Accepted by ICASSP2023

Copy-move forgery on speech (CMF), coupled with post-processing techniques, presents a great challenge to the forensic detection and localization of tampered areas. Most of the existing CMF detection approaches necessitate pre-segmentation of speech to facilitate similarity calculations among these segments. However, these approaches usually suffer from the problems of uncontrollable computational complexity and sensitivity to the presence of a word that is read multiple times within a speech recording. To address these issues, we propose a local feature tensors-based CMF detection algorithm that can transform duplicate detection and localization problems into a special tensor-matching procedure, accompanied by complete theoretical analysis as support. Through extensive experimentation, we have demonstrated that our method exhibits computational efficiency and robustness against post-processing techniques. Notably, it can effectively and blindly detect tampered segments, even those as short as a fractional second. These advantages highlight the promising potential of our approach for practical applications.

Given a recollement of three proper dg algebras over a noetherian commutative ring, e.g. three algebras which are finitely generated over the base ring, which extends one step downwards, it is shown that there is a short exact sequence of their singularity categories. This allows us to recover and generalise some known results on singularity categories of finite-dimensional algebras., Comment: Section 3 is new, and in Section 4 the base ring is changed from a field to a commutative noetherian ring and in Section 6 the base ring is changed from a field to an arbitrary commutative ring

We use the single-dish radio telescope FAST to map the HI in the tidally interacting NGC 4631 group with a resolution of 3.24$'$ (7 kpc), reaching a 5-$\sigma$ column density limit of $10^{17.9}$ cm$^{-2}$ assuming a line width of 20 km s$^{-1}$. Taking the existing interferometric HI image from the HALOGAS project of WSRT as reference, we are able to identify and characterize a significant excess of large-scale, low-density, and diffuse HI in the group. This diffuse HI extends for more than 120 kpc across, and accounts for more than one fourth of the total HI detected by FAST in and around the galaxy NGC 4631. In the region of the tidal tails, the diffuse HI has a typical column density above $10^{19.5}$ cm$^{-2}$, and is highly turbulent with a velocity dispersion around 50 km s$^{-1}$. It increases in column density with the dense HI, and tends to be associated with the kinematically ``hotter'' part of the dense HI. Through simple modeling, we find that the majority of the diffuse HI in the tail region is likely to induce cooling out of the hot IGM instead of evaporating or being radiatively ionized. Given these relations of gas in different phases, the diffuse HI may represent a condensing phase of the IGM. Active tidal interactions on-going and in the past may have produced the wide-spreading HI distribution, and triggered the gas accretion to NGC 4631 through the phase of the diffuse HI., Comment: 35 pages, 24 figures. Accepted for publication at ApJ. FEASTS site: http://kavli.pku.edu.cn/~jwang/FEASTS

We quantitatively characterize the metastability in a multi-phase lattice Boltzmann model. The structure factor of density fluctuations is theoretically obtained and numerically verified to a high precision, for all simulated wave-vectors and reduced temperatures. The static structure factor is found to consistently diverge as the temperature approaches the critical-point or the density approaches the spinodal line at a sub-critical temperature. Theoretically predicted critical exponents are observed in both cases. Finally, the phase separation in the unstable branch follows the same pattern, i.e. the generation of interfaces with different topology, as observed in molecular dynamics simulations. All results can be independently reproduced through the ``idea.deploy" framework https://github.com/lullimat/idea.deploy, Comment: 5 pages, 3 figures, added Supplemental Material in ancillary files

Artificial Intelligence (AI) is having a tremendous impact across most areas of science. Applications of AI in healthcare have the potential to improve our ability to detect, diagnose, prognose, and intervene on human disease. For AI models to be used clinically, they need to be made safe, reproducible and robust, and the underlying software framework must be aware of the particularities (e.g. geometry, physiology, physics) of medical data being processed. This work introduces MONAI, a freely available, community-supported, and consortium-led PyTorch-based framework for deep learning in healthcare. MONAI extends PyTorch to support medical data, with a particular focus on imaging, and provide purpose-specific AI model architectures, transformations and utilities that streamline the development and deployment of medical AI models. MONAI follows best practices for software-development, providing an easy-to-use, robust, well-documented, and well-tested software framework. MONAI preserves the simple, additive, and compositional approach of its underlying PyTorch libraries. MONAI is being used by and receiving contributions from research, clinical and industrial teams from around the world, who are pursuing applications spanning nearly every aspect of healthcare., Comment: www.monai.io

Embedding knowledge graphs (KGs) for multi-hop logical reasoning is a challenging problem due to massive and complicated structures in many KGs. Recently, many promising works projected entities and queries into a geometric space to efficiently find answers. However, it remains challenging to model the negation and union operator. The negation operator has no strict boundaries, which generates overlapped embeddings and leads to obtaining ambiguous answers. An additional limitation is that the union operator is non-closure, which undermines the model to handle a series of union operators. To address these problems, we propose a novel probabilistic embedding model, namely Gamma Embeddings (GammaE), for encoding entities and queries to answer different types of FOL queries on KGs. We utilize the linear property and strong boundary support of the Gamma distribution to capture more features of entities and queries, which dramatically reduces model uncertainty. Furthermore, GammaE implements the Gamma mixture method to design the closed union operator. The performance of GammaE is validated on three large logical query datasets. Experimental results show that GammaE significantly outperforms state-of-the-art models on public benchmarks.

Federated learning (FL) enables building robust and generalizable AI models by leveraging diverse datasets from multiple collaborators without centralizing the data. We created NVIDIA FLARE as an open-source software development kit (SDK) to make it easier for data scientists to use FL in their research and real-world applications. The SDK includes solutions for state-of-the-art FL algorithms and federated machine learning approaches, which facilitate building workflows for distributed learning across enterprises and enable platform developers to create a secure, privacy-preserving offering for multiparty collaboration utilizing homomorphic encryption or differential privacy. The SDK is a lightweight, flexible, and scalable Python package. It allows researchers to apply their data science workflows in any training libraries (PyTorch, TensorFlow, XGBoost, or even NumPy) in real-world FL settings. This paper introduces the key design principles of NVFlare and illustrates some use cases (e.g., COVID analysis) with customizable FL workflows that implement different privacy-preserving algorithms. Code is available at https://github.com/NVIDIA/NVFlare., Comment: Accepted at the International Workshop on Federated Learning, NeurIPS 2022, New Orleans, USA (https://federated-learning.org/fl-neurips-2022); Revised version v2: added Key Components list, system metrics for homomorphic encryption experiment; Extended v3 for journal submission

We conduct a $^{12}$C$^{16}$O($J$=1-0) (hereafter CO) mapping survey of 64 galaxies in the Fornax cluster using the ALMA Morita array in cycle 5. CO emission is detected from 23 out of the 64 galaxies. Our sample includes dwarf, spiral and elliptical galaxies with stellar masses of $M_{\rm star}\sim10^{6.3-11.6}$~M$_\odot$. The achieved beam size and sensitivity are $15''\times8''$ and $\sim12$~mJy~beam$^{-1}$ at the velocity resolution of $\sim10$~km~s$^{-1}$, respectively. We study the cold-gas (molecular- and atomic-gas) properties of 38 subsamples with $M_{\rm star}>10^9$~M$_\odot$ combined with literature HI data. We find that: (1) the low star-formation (SF) activity in the Fornax galaxies is caused by the decrease in the cold-gas mass fraction with respect to stellar mass (hereafter, gas fraction) rather than the decrease of the SF efficiency from the cold gas; (2) the atomic-gas fraction is more heavily reduced than the molecular-gas fraction of such galaxies with low SF activity. A comparison between the cold-gas properties of the Fornax galaxies and their environmental properties suggests that the atomic gas is stripped tidally and by the ram pressure, which leads to the molecular gas depletion with an aid of the strangulation and consequently SF quenching. Pre-processes in the group environment would also play a role in reducing cold-gas reservoirs in some Fornax galaxies., Comment: 53 pages, 41 figures, accepted for publication in ApJS

Head and neck tumor segmentation challenge (HECKTOR) 2022 offers a platform for researchers to compare their solutions to segmentation of tumors and lymph nodes from 3D CT and PET images. In this work, we describe our solution to HECKTOR 2022 segmentation task. We re-sample all images to a common resolution, crop around head and neck region, and train SegResNet semantic segmentation network from MONAI. We use 5-fold cross validation to select best model checkpoints. The final submission is an ensemble of 15 models from 3 runs. Our solution (team name NVAUTO) achieves the 1st place on the HECKTOR22 challenge leaderboard with an aggregated dice score of 0.78802., Comment: HECKTOR22 segmentation challenge. MICCAI 2022. arXiv admin note: text overlap with arXiv:2209.09546

Intracranial hemorrhage segmentation challenge (INSTANCE 2022) offers a platform for researchers to compare their solutions to segmentation of hemorrhage stroke regions from 3D CTs. In this work, we describe our solution to INSTANCE 2022. We use a 2D segmentation network, SegResNet from MONAI, operating slice-wise without resampling. The final submission is an ensemble of 18 models. Our solution (team name NVAUTO) achieves the top place in terms of Dice metric (0.721), and overall rank 2. It is implemented with Auto3DSeg., Comment: INSTANCE22 challenge report, MICCAI2022. arXiv admin note: substantial text overlap with arXiv:2209.09546

Ischemic Stroke Lesion Segmentation challenge (ISLES 2022) offers a platform for researchers to compare their solutions to 3D segmentation of ischemic stroke regions from 3D MRIs. In this work, we describe our solution to ISLES 2022 segmentation task. We re-sample all images to a common resolution, use two input MRI modalities (DWI and ADC) and train SegResNet semantic segmentation network from MONAI. The final submission is an ensemble of 15 models (from 3 runs of 5-fold cross validation). Our solution (team name NVAUTO) achieves the top place in terms of Dice metric (0.824), and overall rank 2 (based on the combined metric ranking)., Comment: ISLES22 challenge report, MICCAI2022

Which volume to annotate next is a challenging problem in building medical imaging datasets for deep learning. One of the promising methods to approach this question is active learning (AL). However, AL has been a hard nut to crack in terms of which AL algorithm and acquisition functions are most useful for which datasets. Also, the problem is exacerbated with which volumes to label first when there is zero labeled data to start with. This is known as the cold start problem in AL. We propose two novel strategies for AL specifically for 3D image segmentation. First, we tackle the cold start problem by proposing a proxy task and then utilizing uncertainty generated from the proxy task to rank the unlabeled data to be annotated. Second, we craft a two-stage learning framework for each active iteration where the unlabeled data is also used in the second stage as a semi-supervised fine-tuning strategy. We show the promise of our approach on two well-known large public datasets from medical segmentation decathlon. The results indicate that the initial selection of data and semi-supervised framework both showed significant improvement for several AL strategies., Comment: 12 pages, 5 figures

The Kalman filter has been adopted in acoustic echo cancellation due to its robustness to double-talk, fast convergence, and good steady-state performance. The performance of Kalman filter is closely related to the estimation accuracy of the state noise covariance and the observation noise covariance. The estimation error may lead to unacceptable results, especially when the echo path suffers abrupt changes, the tracking performance of the Kalman filter could be degraded significantly. In this paper, we propose the neural Kalman filtering (NKF), which uses neural networks to implicitly model the covariance of the state noise and observation noise and to output the Kalman gain in real-time. Experimental results on both synthetic test sets and real-recorded test sets show that, the proposed NKF has superior convergence and re-convergence performance while ensuring low near-end speech degradation comparing with the state-of-the-art model-based methods. Moreover, the model size of the proposed NKF is merely 5.3 K and the RTF is as low as 0.09, which indicates that it can be deployed in low-resource platforms.

In recent studies, moving target defense (MTD) has been applied to detect false data injection (FDI) attacks using distributed flexible AC transmission system (D-FACTS) devices. However, the inherent conflict between the security goals of MTD (i.e., detecting FDI attacks) and the economic goals of D-FACTS devices (i.e., reducing power losses) would impede the application of MTD in real systems. Moreover, the detection capabilities of existing MTDs are often insufficient. This paper proposes a multi-stage MTD (MMTD) approach to resolve these two issues by adding a group of designed security-oriented schemes before D-FACTS' economic-oriented scheme to detect FDI attacks. We keep these security-oriented schemes for a very short time interval and then revert to the economic-oriented scheme for the remaining time to ensure the economic requirements. We prove that a designed MMTD can significantly improve the detection capability compared to existing one-stage MTDs. We find the supremum of MMTD's detection capability and study its relationship with system topology and D-FACTS deployment. Meanwhile, a greedy algorithm is proposed to search the MMTD strategy to reach this supremum. Simulation results show that the proposed MMTD can achieve the supremum against FDI attacks while outperforming current MTD strategies on economic indicators., Comment: 10 pages, 10 figures

An extended version of Riedtmann's Lie algebra of the gentle one-cycle algebra $\Lambda(n-1,1,1)$ is computed and is shown to admit a Cartan decomposition by the positive roots of the root system of type $\mathbf{BC}_n$., Comment: Minor changes

Vision Transformers (ViT)s have recently become popular due to their outstanding modeling capabilities, in particular for capturing long-range information, and scalability to dataset and model sizes which has led to state-of-the-art performance in various computer vision and medical image analysis tasks. In this work, we introduce a unified framework consisting of two architectures, dubbed UNetFormer, with a 3D Swin Transformer-based encoder and Convolutional Neural Network (CNN) and transformer-based decoders. In the proposed model, the encoder is linked to the decoder via skip connections at five different resolutions with deep supervision. The design of proposed architecture allows for meeting a wide range of trade-off requirements between accuracy and computational cost. In addition, we present a methodology for self-supervised pre-training of the encoder backbone via learning to predict randomly masked volumetric tokens using contextual information of visible tokens. We pre-train our framework on a cohort of $5050$ CT images, gathered from publicly available CT datasets, and present a systematic investigation of various components such as masking ratio and patch size that affect the representation learning capability and performance of downstream tasks. We validate the effectiveness of our pre-training approach by fine-tuning and testing our model on liver and liver tumor segmentation task using the Medical Segmentation Decathlon (MSD) dataset and achieve state-of-the-art performance in terms of various segmentation metrics. To demonstrate its generalizability, we train and test the model on BraTS 21 dataset for brain tumor segmentation using MRI images and outperform other methods in terms of Dice score. Code: https://github.com/Project-MONAI/research-contributions, Comment: Tech. report, 12 pages, 3 figures

Cross-silo federated learning (FL) has attracted much attention in medical imaging analysis with deep learning in recent years as it can resolve the critical issues of insufficient data, data privacy, and training efficiency. However, there can be a generalization gap between the model trained from FL and the one from centralized training. This important issue comes from the non-iid data distribution of the local data in the participating clients and is well-known as client drift. In this work, we propose a novel training framework FedSM to avoid the client drift issue and successfully close the generalization gap compared with the centralized training for medical image segmentation tasks for the first time. We also propose a novel personalized FL objective formulation and a new method SoftPull to solve it in our proposed framework FedSM. We conduct rigorous theoretical analysis to guarantee its convergence for optimizing the non-convex smooth objective function. Real-world medical image segmentation experiments using deep FL validate the motivations and effectiveness of our proposed method., Comment: CVPR 2022

Federated learning (FL) is a distributed machine learning technique that enables collaborative model training while avoiding explicit data sharing. The inherent privacy-preserving property of FL algorithms makes them especially attractive to the medical field. However, in case of heterogeneous client data distributions, standard FL methods are unstable and require intensive hyperparameter tuning to achieve optimal performance. Conventional hyperparameter optimization algorithms are impractical in real-world FL applications as they involve numerous training trials, which are often not affordable with limited compute budgets. In this work, we propose an efficient reinforcement learning (RL)-based federated hyperparameter optimization algorithm, termed Auto-FedRL, in which an online RL agent can dynamically adjust hyperparameters of each client based on the current training progress. Extensive experiments are conducted to investigate different search strategies and RL agents. The effectiveness of the proposed method is validated on a heterogeneous data split of the CIFAR-10 dataset as well as two real-world medical image segmentation datasets for COVID-19 lesion segmentation in chest CT and pancreas segmentation in abdominal CT.

Heat exchanger tube rows can influence the thermoacoustic instability behaviour of combustion systems since they act as both acoustic scatterers and unsteady heat sinks. Therefore, with careful tuning of their thermoacoustic properties, heat exchangers have the potential to act as passive control devices. In this work, we focus on (only) the acoustic scattering behaviour of heat exchanger tubes. We present a comparison of existing acoustic models for tube rows and slits, models for the latter having the advantage of incorporating frequency dependence. We then propose a new model that enables the adaptation of slit models for tube rows. This model is validated against experiments and Linearised Navier Stokes Equations (LNSE) predictions for the transmission and reflection coefficients, including phase information. The model predictions show very good agreement with the experimental and numerical validations, especially for low frequencies (Strouhal number < 0.5, based on tube radius and excitation frequency), with mean differences less than 2% for the transmission coefficients (the reflection coefficient errors are somewhat larger since their magnitudes are very close to zero)., Comment: 23 pages, 10 figures, to be published in the Journal of Sound and Vibration