arXiv subjects

Yan Xia

Publications and source records attributed to Yan Xia.

At least 163 records · Page 9Linked to original sources

arXiv2023

CASSPR: Cross Attention Single Scan Place Recognition

Place recognition based on point clouds (LiDAR) is an important component for autonomous robots or self-driving vehicles. Current SOTA performance is achieved on accumulated LiDAR submaps using either point-based or voxel-based structures. While voxel-based approaches nicely integrate spatial context across multiple scales, they do not exhibit the local precision of point-based methods. As a result, existing methods struggle with fine-grained matching of subtle geometric features in sparse single-shot Li- DAR scans. To overcome these limitations, we propose CASSPR as a method to fuse point-based and voxel-based approaches using cross attention transformers. CASSPR leverages a sparse voxel branch for extracting and aggregating information at lower resolution and a point-wise branch for obtaining fine-grained local information. CASSPR uses queries from one branch to try to match structures in the other branch, ensuring that both extract self-contained descriptors of the point cloud (rather than one branch dominating), but using both to inform the output global descriptor of the point cloud. Extensive experiments show that CASSPR surpasses the state-of-the-art by a large margin on several datasets (Oxford RobotCar, TUM, USyd). For instance, it achieves AR@1 of 85.6% on the TUM dataset, surpassing the strongest prior model by ~15%. Our code is publicly available.

cs.CV↗

arXiv2023

Learned Local Attention Maps for Synthesising Vessel Segmentations

Magnetic resonance angiography (MRA) is an imaging modality for visualising blood vessels. It is useful for several diagnostic applications and for assessing the risk of adverse events such as haemorrhagic stroke (resulting from the rupture of aneurysms in blood vessels). However, MRAs are not acquired routinely, hence, an approach to synthesise blood vessel segmentations from more routinely acquired MR contrasts such as T1 and T2, would be useful. We present an encoder-decoder model for synthesising segmentations of the main cerebral arteries in the circle of Willis (CoW) from only T2 MRI. We propose a two-phase multi-objective learning approach, which captures both global and local features. It uses learned local attention maps generated by dilating the segmentation labels, which forces the network to only extract information from the T2 MRI relevant to synthesising the CoW. Our synthetic vessel segmentations generated from only T2 MRI achieved a mean Dice score of $0.79 \pm 0.03$ in testing, compared to state-of-the-art segmentation networks such as transformer U-Net ($0.71 \pm 0.04$) and nnU-net($0.68 \pm 0.05$), while using only a fraction of the parameters. The main qualitative difference between our synthetic vessel segmentations and the comparative models was in the sharper resolution of the CoW vessel segments, especially in the posterior circulation.

eess.IV↗

arXiv2023

Adaptive Semi-Supervised Segmentation of Brain Vessels with Ambiguous Labels

Accurate segmentation of brain vessels is crucial for cerebrovascular disease diagnosis and treatment. However, existing methods face challenges in capturing small vessels and handling datasets that are partially or ambiguously annotated. In this paper, we propose an adaptive semi-supervised approach to address these challenges. Our approach incorporates innovative techniques including progressive semi-supervised learning, adaptative training strategy, and boundary enhancement. Experimental results on 3DRA datasets demonstrate the superiority of our method in terms of mesh-based segmentation metrics. By leveraging the partially and ambiguously labeled data, which only annotates the main vessels, our method achieves impressive segmentation performance on mislabeled fine vessels, showcasing its potential for clinical applications.

eess.IV↗

arXiv2023

The Russian invasion of Ukraine selectively depolarized the Finnish NATO discussion

The Russian invasion of Ukraine in 2022 dramatically reshaped the European security landscape. In Finland, public opinion on NATO had long been polarized along the left-right partisan axis, but the invasion led to a rapid convergence of the opinion toward joining NATO. We investigate whether and how this depolarization took place among polarized actors on Finnish Twitter. By analyzing retweeting patterns, we find three separated user groups before the invasion: a pro-NATO, a left-wing anti-NATO, and a conspiracy-charged anti-NATO group. After the invasion, the left-wing anti-NATO group members broke out of their retweeting bubble and connected with the pro-NATO group despite their difference in partisanship, while the conspiracy-charged anti-NATO group mostly remained a separate cluster. Our content analysis reveals that the left-wing anti-NATO group and the pro-NATO group were bridged by a shared condemnation of Russia's actions and shared democratic norms, while the other anti-NATO group, mainly built around conspiracy theories and disinformation, consistently demonstrated a clear anti-NATO attitude. We show that an external threat can bridge partisan divides in issues linked to the threat, but bubbles upheld by conspiracy theories and disinformation may persist even under dramatic external threats.

cs.SI↗

arXiv2023

Robust transitionless quantum driving: Concatenated approach

We propose a concatenated approach for implementing transitionless quantum driving regardless of adiabatic conditions while being robustness with respect to all kinds of systematic errors induced by pulse duration, pulse amplitude, detunings, and Stark shift, etc. The current approach is particularly efficient for all time-dependent pulses with arbitrary shape, and only the phase differences between pulses is required to properly modulate. The simple physical implementation without the help of pulse shaping techniques or extra pulses makes this approach quite universal and provides a different avenue for robust quantum control by the time-dependent Hamiltonian.

quant-ph↗

arXiv2023

Assessing Phrase Break of ESL Speech with Pre-trained Language Models and Large Language Models

This work introduces approaches to assessing phrase breaks in ESL learners' speech using pre-trained language models (PLMs) and large language models (LLMs). There are two tasks: overall assessment of phrase break for a speech clip and fine-grained assessment of every possible phrase break position. To leverage NLP models, speech input is first force-aligned with texts, and then pre-processed into a token sequence, including words and phrase break information. To utilize PLMs, we propose a pre-training and fine-tuning pipeline with the processed tokens. This process includes pre-training with a replaced break token detection module and fine-tuning with text classification and sequence labeling. To employ LLMs, we design prompts for ChatGPT. The experiments show that with the PLMs, the dependence on labeled training data has been greatly reduced, and the performance has improved. Meanwhile, we verify that ChatGPT, a renowned LLM, has potential for further advancement in this area.

cs.CL↗

arXiv2023

Smart Word Suggestions for Writing Assistance

Enhancing word usage is a desired feature for writing assistance. To further advance research in this area, this paper introduces "Smart Word Suggestions" (SWS) task and benchmark. Unlike other works, SWS emphasizes end-to-end evaluation and presents a more realistic writing assistance scenario. This task involves identifying words or phrases that require improvement and providing substitution suggestions. The benchmark includes human-labeled data for testing, a large distantly supervised dataset for training, and the framework for evaluation. The test data includes 1,000 sentences written by English learners, accompanied by over 16,000 substitution suggestions annotated by 10 native speakers. The training dataset comprises over 3.7 million sentences and 12.7 million suggestions generated through rules. Our experiments with seven baselines demonstrate that SWS is a challenging task. Based on experimental analysis, we suggest potential directions for future research on SWS. The dataset and related codes is available at https://github.com/microsoft/SmartWordSuggestions.

cs.CL↗

arXiv2023

Scan2LoD3: Reconstructing semantic 3D building models at LoD3 using ray casting and Bayesian networks

Reconstructing semantic 3D building models at the level of detail (LoD) 3 is a long-standing challenge. Unlike mesh-based models, they require watertight geometry and object-wise semantics at the façade level. The principal challenge of such demanding semantic 3D reconstruction is reliable façade-level semantic segmentation of 3D input data. We present a novel method, called Scan2LoD3, that accurately reconstructs semantic LoD3 building models by improving façade-level semantic 3D segmentation. To this end, we leverage laser physics and 3D building model priors to probabilistically identify model conflicts. These probabilistic physical conflicts propose locations of model openings: Their final semantics and shapes are inferred in a Bayesian network fusing multimodal probabilistic maps of conflicts, 3D point clouds, and 2D images. To fulfill demanding LoD3 requirements, we use the estimated shapes to cut openings in 3D building priors and fit semantic 3D objects from a library of façade objects. Extensive experiments on the TUM city campus datasets demonstrate the superior performance of the proposed Scan2LoD3 over the state-of-the-art methods in façade-level detection, semantic segmentation, and LoD3 building model reconstruction. We believe our method can foster the development of probability-driven semantic 3D reconstruction at LoD3 since not only the high-definition reconstruction but also reconstruction confidence becomes pivotal for various applications such as autonomous driving and urban simulations.

cs.CV↗

arXiv2023

Effective dynamics and quantum state engineering by periodic kicks

We study the kick dynamics of periodically driven quantum systems, and provide a timeindependent effective Hamiltonian with the analytical form to reasonably describe the effective dynamics in a long timescale. It is shown that the effective coupling strength can be much larger than the coupling strength of the original system in some parameter regions, which stems from the zero time duration of kicks. Furthermore, different regimes can be transformed from and to each other in the same three-level system by only modulating the period of periodic kicks. In particular, the population of excited states can be selectively suppressed in periodic kicks, benefiting from the large detuning regime of the original system. Finally, some applications and physical implementation of periodic kicks are demonstrated in quantum systems. Those unique features would make periodic kicks becoming a powerful tool for quantum state engineering.

quant-ph↗

arXiv2023

TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs

Artificial Intelligence (AI) has made incredible progress recently. On the one hand, advanced foundation models like ChatGPT can offer powerful conversation, in-context learning and code generation abilities on a broad range of open-domain tasks. They can also generate high-level solution outlines for domain-specific tasks based on the common sense knowledge they have acquired. However, they still face difficulties with some specialized tasks because they lack enough domain-specific data during pre-training or they often have errors in their neural network computations on those tasks that need accurate executions. On the other hand, there are also many existing models and systems (symbolic-based or neural-based) that can do some domain-specific tasks very well. However, due to the different implementation or working mechanisms, they are not easily accessible or compatible with foundation models. Therefore, there is a clear and pressing need for a mechanism that can leverage foundation models to propose task solution outlines and then automatically match some of the sub-tasks in the outlines to the off-the-shelf models and systems with special functionalities to complete them. Inspired by this, we introduce TaskMatrix.AI as a new AI ecosystem that connects foundation models with millions of APIs for task completion. Unlike most previous work that aimed to improve a single AI model, TaskMatrix.AI focuses more on using existing foundation models (as a brain-like central system) and APIs of other AI models and systems (as sub-task solvers) to achieve diversified tasks in both digital and physical domains. As a position paper, we will present our vision of how to build such an ecosystem, explain each key component, and use study cases to illustrate both the feasibility of this vision and the main challenges we need to address next.

cs.AI↗

arXiv2023

Generation of spin squeezing via a fully quantum degenerate parametric amplifier

Spin squeezing is one of the most attractive methods for realizing high-precision metrology. In this paper, we propose a protocol for generating spin squeezing in an atomic ensemble via a fully quantum degenerate parametric amplifier. We discuss the properties of generating spin squeezing with and without driving the pump cavity. Numerical simulation results show that the generated spin squeezing strength is sizable, and is able to be comparable to that obtained using a two-axis twisting (TAT) model. Moreover, we demonstrate that the protocol is experimentally feasible by introducing the corresponding experimental parameters. Therefore, the proposed protocol provides a promising approach to realize spin squeezing in photon-spin coupling systems.

quant-ph↗

arXiv2023

A Lightweight and Detector-free 3D Single Object Tracker on Point Clouds

Recent works on 3D single object tracking treat the task as a target-specific 3D detection task, where an off-the-shelf 3D detector is commonly employed for the tracking. However, it is non-trivial to perform accurate target-specific detection since the point cloud of objects in raw LiDAR scans is usually sparse and incomplete. In this paper, we address this issue by explicitly leveraging temporal motion cues and propose DMT, a Detector-free Motion-prediction-based 3D Tracking network that completely removes the usage of complicated 3D detectors and is lighter, faster, and more accurate than previous trackers. Specifically, the motion prediction module is first introduced to estimate a potential target center of the current frame in a point-cloud-free manner. Then, an explicit voting module is proposed to directly regress the 3D box from the estimated target center. Extensive experiments on KITTI and NuScenes datasets demonstrate that our DMT can still achieve better performance (~10% improvement over the NuScenes dataset) and a faster tracking speed (i.e., 72 FPS) than state-of-the-art approaches without applying any complicated 3D detectors. Our code is released at \url{https://github.com/jimmy-dq/DMT}

cs.CV↗

arXiv2023

Unsupervised ensemble-based phenotyping helps enhance the discoverability of genes related to heart morphology

Recent genome-wide association studies (GWAS) have been successful in identifying associations between genetic variants and simple cardiac parameters derived from cardiac magnetic resonance (CMR) images. However, the emergence of big databases including genetic data linked to CMR, facilitates investigation of more nuanced patterns of shape variability. Here, we propose a new framework for gene discovery entitled Unsupervised Phenotype Ensembles (UPE). UPE builds a redundant yet highly expressive representation by pooling a set of phenotypes learned in an unsupervised manner, using deep learning models trained with different hyperparameters. These phenotypes are then analyzed via (GWAS), retaining only highly confident and stable associations across the ensemble. We apply our approach to the UK Biobank database to extract left-ventricular (LV) geometric features from image-derived three-dimensional meshes. We demonstrate that our approach greatly improves the discoverability of genes influencing LV shape, identifying 11 loci with study-wide significance and 8 with suggestive significance. We argue that our approach would enable more extensive discovery of gene associations with image-derived phenotypes for other organs or image modalities.

q-bio.GN↗

arXiv2022

Enhanced-Fidelity Ultrafast Geometric Quantum Computation Using Strong Classical Drives

We propose a general approach to implement nonadiabatic geometric single- and two-qubit gates beyond the rotating wave approximation (RWA). This protocol is compatible with most optimal control methods used in previous RWA protocols; thus, it is as robust as (or even more robust than) the RWA protocols. Using counter-rotating effects allows us to apply strong drives. Therefore, we can improve the gate speed by 5--10 times compared to the RWA counterpart for implementing high-fidelity ($\geq 99.99\%$) gates. Such an ultrafast evolution (nanoseconds, even picoseconds) significantly reduces the influence of decoherence (e.g., the qubit dissipation and dephasing). Moreover, because the counter-rotating effects no longer induce gate infidelities (in both the weak and strong driving regimes), we can achieve a higher fidelity compared to the RWA protocols. Therefore, in the presence of decoherence, one can implement ultrafast geometric quantum gates with $\geq 99\%$ fidelities.

quant-ph↗

arXiv2022

Joint segmentation and discontinuity-preserving deformable registration: Application to cardiac cine-MR images

Medical image registration is a challenging task involving the estimation of spatial transformations to establish anatomical correspondence between pairs or groups of images. Recently, deep learning-based image registration methods have been widely explored, and demonstrated to enable fast and accurate image registration in a variety of applications. However, most deep learning-based registration methods assume that the deformation fields are smooth and continuous everywhere in the image domain, which is not always true, especially when registering images whose fields of view contain discontinuities at tissue/organ boundaries. In such scenarios, enforcing smooth, globally continuous deformation fields leads to incorrect/implausible registration results. We propose a novel discontinuity-preserving image registration method to tackle this challenge, which ensures globally discontinuous and locally smooth deformation fields, leading to more accurate and realistic registration results. The proposed method leverages the complementary nature of image segmentation and registration and enables joint segmentation and pair-wise registration of images. A co-attention block is proposed in the segmentation component of the network to learn the structural correlations in the input images, while a discontinuity-preserving registration strategy is employed in the registration component of the network to ensure plausibility in the estimated deformation fields at tissue/organ interfaces. We evaluate our method on the task of intra-subject spatio-temporal image registration using large-scale cinematic cardiac magnetic resonance image sequences, and demonstrate that our method achieves significant improvements over the state-of-the-art for medical image registration, and produces high-quality segmentation masks for the regions of interest.

cs.CV↗

arXiv2022

Assessing Phrase Break of ESL speech with Pre-trained Language Models

This work introduces an approach to assessing phrase break in ESL learners' speech with pre-trained language models (PLMs). Different with traditional methods, this proposal converts speech to token sequences, and then leverages the power of PLMs. There are two sub-tasks: overall assessment of phrase break for a speech clip; fine-grained assessment of every possible phrase break position. Speech input is first force-aligned with texts, then pre-processed to a token sequence, including words and associated phrase break information. The token sequence is then fed into the pre-training and fine-tuning pipeline. In pre-training, a replaced break token detection module is trained with token data where each token has a certain percentage chance to be randomly replaced. In fine-tuning, overall and fine-grained scoring are optimized with text classification and sequence labeling pipeline, respectively. With the introduction of PLMs, the dependence on labeled training data has been greatly reduced, and performance has improved.

cs.CL↗

arXiv2022

Video-Guided Curriculum Learning for Spoken Video Grounding

In this paper, we introduce a new task, spoken video grounding (SVG), which aims to localize the desired video fragments from spoken language descriptions. Compared with using text, employing audio requires the model to directly exploit the useful phonemes and syllables related to the video from raw speech. Moreover, we randomly add environmental noises to this speech audio, further increasing the difficulty of this task and better simulating real applications. To rectify the discriminative phonemes and extract video-related information from noisy audio, we develop a novel video-guided curriculum learning (VGCL) during the audio pre-training process, which can make use of the vital visual perceptions to help understand the spoken language and suppress the external noise. Considering during inference the model can not obtain ground truth video segments, we design a curriculum strategy that gradually shifts the input video from the ground truth to the entire video content during pre-training. Finally, the model can learn how to extract critical visual information from the entire video clip to help understand the spoken language. In addition, we collect the first large-scale spoken video grounding dataset based on ActivityNet, which is named as ActivityNet Speech dataset. Extensive experiments demonstrate our proposed video-guided curriculum learning can facilitate the pre-training process to obtain a mutual audio encoder, significantly promoting the performance of spoken video grounding tasks. Moreover, we prove that in the case of noisy sound, our model outperforms the method that grounding video with ASR transcripts, further demonstrating the effectiveness of our curriculum strategy.

cs.CV↗

arXiv2022

Tripartite high-dimensional magnon-photon entanglement in PT -symmetry broken phases of a non-Hermitian hybrid system

Hybrid systems that combine spin ensembles and superconducting circuits provide a promising platform for implementing quantum information processing. We propose a non-Hermitian magnoncircuit-QED hybrid model consisting of two cavities and an yttrium iron garnet (YIG) sphere placed in one of the cavities. Abundant exceptional points (EPs), parity-time (PT )-symmetry phases and PT -symmetry broken phases are investigated in the parameter space. Tripartite highdimensional entangled states can be generated steadily among modes of the magnon and photons in PT -symmetry broken phases, corresponding to which the stable quantum coherence exists. Results show that the tripartite high-dimensional entangled state is robust against the dissipation of hybrid system, independent of a certain initial state, and insensitive to the fluctuation of magnonphoton coupling. Further, we propose to simulate the hybrid model with an equivalent LCR circuit. This work may provide prospects for realizing multipartite high-dimensional entangled states in the magnon-circuit-QED hybrid system.

quant-ph↗