Searcharxiv⌕ Search

arXiv subjects

Xinyang Liu

Publications and source records attributed to Xinyang Liu.

67 records · Page 4Linked to original sources
arXiv2023

1720nm-1800nm tunable chirped pulse amplification based on thulium-doped fiber

Chirped pulse amplification (CPA) has been adopted as a commonly used methodology to obtain powerful ultrashort laser pulses since its first demonstration. However, wavelength-tunable CPA systems are rarely reported. Wavelength-tunable ultrashort and intense laser pulses are desired in various fields like nonlinear spectroscopy and optical parametric amplification. In this work, we report a 1720 nm -1800 nm tunable CPA system based on a single-mode Tm-doped fiber covering the middle wavelength band of the third biological window. The tunable CPA system delivers ultrashort pulses varied between ~300 to 500 fs depending on the central wavelength emission at the fixed repetition rate of 22.7 MHz. The maximum average power ranges from 126 mW at 1720 nm to 294 mW at 1800 nm following the gain shape of Tm-doped fiber. Considering the specific wave-length range, this tunable CPA system is highly desired for biomedical imaging, sensing and parametric amplifiers for mid-infrared light generation.

physics.optics↗
arXiv2023

Predicting mode-locked fiber laser output using feed-forward neural network

With a great ability to solve regression problems, the artificial neural network has become a powerful tool to facilitate advancing ultrafast laser research. In this contribution, we demonstrate the capability of a feed-forward neural network (FNN) to predict the output parameters of a mode-locked fiber laser, which mutually depend on multiple intracavity parameters, with high speed and accuracy. A direct mapping between cavity parameters and laser output is realized through the FNN-trained models, bypassing tedious iterative numerical simulation as a common approach to get a converged solution for a laser cavity. We show that the laser output spectrum and temporal pulse profiles can be accurately predicted with the normalized root mean square error (NRMSE) of less than 0.032 within only a 5 ms time frame for scenarios inside and outside the training data. We investigate the influence of FNN configuration on prediction performance. Both gain and spectral filter parameters are explored to test the prediction capability of the trained FNN models at high speed. Straightforward and fast prediction of the laser output performance for varying laser intracavity parameters paves the way to intelligent short-pulsed lasers with inversed design or autonomous operation maintenance.

physics.optics↗
arXiv2023

Tuning Multi-mode Token-level Prompt Alignment across Modalities

Advancements in prompt tuning of vision-language models have underscored their potential in enhancing open-world visual concept comprehension. However, prior works only primarily focus on single-mode (only one prompt for each modality) and holistic level (image or sentence) semantic alignment, which fails to capture the sample diversity, leading to sub-optimal prompt discovery. To address the limitation, we propose a multi-mode token-level tuning framework that leverages the optimal transportation to learn and align a set of prompt tokens across modalities. Specifically, we rely on two essential factors: 1) multi-mode prompts discovery, which guarantees diverse semantic representations, and 2) token-level alignment, which helps explore fine-grained similarity. Consequently, the similarity can be calculated as a hierarchical transportation problem between the modality-specific sets. Extensive experiments on popular image recognition benchmarks show the superior generalization and few-shot abilities of our approach. The qualitative analysis demonstrates that the learned prompt tokens have the ability to capture diverse visual concepts.

cs.CV↗
arXiv2023

Multi-Modal Neural Radiance Field for Monocular Dense SLAM with a Light-Weight ToF Sensor

Light-weight time-of-flight (ToF) depth sensors are compact and cost-efficient, and thus widely used on mobile devices for tasks such as autofocus and obstacle detection. However, due to the sparse and noisy depth measurements, these sensors have rarely been considered for dense geometry reconstruction. In this work, we present the first dense SLAM system with a monocular camera and a light-weight ToF sensor. Specifically, we propose a multi-modal implicit scene representation that supports rendering both the signals from the RGB camera and light-weight ToF sensor which drives the optimization by comparing with the raw sensor inputs. Moreover, in order to guarantee successful pose tracking and reconstruction, we exploit a predicted depth as an intermediate supervision and develop a coarse-to-fine optimization strategy for efficient learning of the implicit representation. At last, the temporal information is explicitly exploited to deal with the noisy signals from light-weight ToF sensors to improve the accuracy and robustness of the system. Experiments demonstrate that our system well exploits the signals of light-weight ToF sensors and achieves competitive results both on camera tracking and dense scene reconstruction. Project page: \url{https://zju3dv.github.io/tof_slam/}.

cs.CV↗
arXiv2023

PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classification

Multi-label image classification is a prediction task that aims to identify more than one label from a given image. This paper considers the semantic consistency of the latent space between the visual patch and linguistic label domains and introduces the conditional transport (CT) theory to bridge the acknowledged gap. While recent cross-modal attention-based studies have attempted to align such two representations and achieved impressive performance, they required carefully-designed alignment modules and extra complex operations in the attention computation. We find that by formulating the multi-label classification as a CT problem, we can exploit the interactions between the image and label efficiently by minimizing the bidirectional CT cost. Specifically, after feeding the images and textual labels into the modality-specific encoders, we view each image as a mixture of patch embeddings and a mixture of label embeddings, which capture the local region features and the class prototypes, respectively. CT is then employed to learn and align those two semantic sets by defining the forward and backward navigators. Importantly, the defined navigators in CT distance model the similarities between patches and labels, which provides an interpretable tool to visualize the learned prototypes. Extensive experiments on three public image benchmarks show that the proposed model consistently outperforms the previous methods.

cs.CV↗
arXiv2023

The Brain Tumor Segmentation (BraTS) Challenge 2023: Glioma Segmentation in Sub-Saharan Africa Patient Population (BraTS-Africa)

Gliomas are the most common type of primary brain tumors. Although gliomas are relatively rare, they are among the deadliest types of cancer, with a survival rate of less than 2 years after diagnosis. Gliomas are challenging to diagnose, hard to treat and inherently resistant to conventional therapy. Years of extensive research to improve diagnosis and treatment of gliomas have decreased mortality rates across the Global North, while chances of survival among individuals in low- and middle-income countries (LMICs) remain unchanged and are significantly worse in Sub-Saharan Africa (SSA) populations. Long-term survival with glioma is associated with the identification of appropriate pathological features on brain MRI and confirmation by histopathology. Since 2012, the Brain Tumor Segmentation (BraTS) Challenge have evaluated state-of-the-art machine learning methods to detect, characterize, and classify gliomas. However, it is unclear if the state-of-the-art methods can be widely implemented in SSA given the extensive use of lower-quality MRI technology, which produces poor image contrast and resolution and more importantly, the propensity for late presentation of disease at advanced stages as well as the unique characteristics of gliomas in SSA (i.e., suspected higher rates of gliomatosis cerebri). Thus, the BraTS-Africa Challenge provides a unique opportunity to include brain MRI glioma cases from SSA in global efforts through the BraTS Challenge to develop and evaluate computer-aided-diagnostic (CAD) methods for the detection and characterization of glioma in resource-limited settings, where the potential for CAD tools to transform healthcare are more likely.

eess.IV↗
arXiv2023

The ASNR-MICCAI Brain Tumor Segmentation (BraTS) Challenge 2023: Intracranial Meningioma

Meningiomas are the most common primary intracranial tumor in adults and can be associated with significant morbidity and mortality. Radiologists, neurosurgeons, neuro-oncologists, and radiation oncologists rely on multiparametric MRI (mpMRI) for diagnosis, treatment planning, and longitudinal treatment monitoring; yet automated, objective, and quantitative tools for non-invasive assessment of meningiomas on mpMRI are lacking. The BraTS meningioma 2023 challenge will provide a community standard and benchmark for state-of-the-art automated intracranial meningioma segmentation models based on the largest expert annotated multilabel meningioma mpMRI dataset to date. Challenge competitors will develop automated segmentation models to predict three distinct meningioma sub-regions on MRI including enhancing tumor, non-enhancing tumor core, and surrounding nonenhancing T2/FLAIR hyperintensity. Models will be evaluated on separate validation and held-out test datasets using standardized metrics utilized across the BraTS 2023 series of challenges including the Dice similarity coefficient and Hausdorff distance. The models developed during the course of this challenge will aid in incorporation of automated meningioma MRI segmentation into clinical practice, which will ultimately improve care of patients with meningioma.

cs.CV↗
arXiv2022

DELTAR: Depth Estimation from a Light-weight ToF Sensor and RGB Image

Light-weight time-of-flight (ToF) depth sensors are small, cheap, low-energy and have been massively deployed on mobile devices for the purposes like autofocus, obstacle detection, etc. However, due to their specific measurements (depth distribution in a region instead of the depth value at a certain pixel) and extremely low resolution, they are insufficient for applications requiring high-fidelity depth such as 3D reconstruction. In this paper, we propose DELTAR, a novel method to empower light-weight ToF sensors with the capability of measuring high resolution and accurate depth by cooperating with a color image. As the core of DELTAR, a feature extractor customized for depth distribution and an attention-based neural architecture is proposed to fuse the information from the color and ToF domain efficiently. To evaluate our system in real-world scenarios, we design a data collection device and propose a new approach to calibrate the RGB camera and ToF sensor. Experiments show that our method produces more accurate depth than existing frameworks designed for depth completion and depth super-resolution and achieves on par performance with a commodity-level RGB-D sensor. Code and data are available at https://zju3dv.github.io/deltar/.

cs.CV↗
arXiv2022

Identification of the decay pathway of photoexcited nucleobases

The identification of the decay pathway of the nucleobase uracil after being photoexcited by ultraviolet (UV) light has been a long standing problem. Various theoretical models have been proposed but yet to be verified. Here we propose an experimental scheme to test the theoretical models by a combination of ultrafast X-ray spectroscopy, X-ray diffraction and electron diffraction methods. Incorporating the signatures of multiple probing methods, we demonstrate an approach to identify the pathway of the geometric and electronic relaxation of the photoexcited uracil molecule.

physics.chem-ph↗
arXiv2021

What do neuroanatomical networks reveal about the ontology of human cognitive abilities?

Over the last decades, cognitive psychology has come to fair consensus about the ontological structure of human intelligence. However, it remains an open question, whether anatomical properties of the brain support the same ontology. The present study explored the ontological structure derived from neuroanatomical networks associated with performance in 15 cognitive tasks indicating various abilities. Results suggest that the brain-derived (neurometric) ontology is partly consistent with the cognitive performance-derived (psychometric) ontology. However, there are interpretable and complementary differences as well. Moreover, the cortical areas associated with different inferred abilities are segregated, with little or no overlap. Nevertheless, these spatially segregated cortical areas are integrated via denser white matter structural connections as compared with the general brain connectome. The integration of ability-related cortical networks constitutes a neural counterpart to the psychometric construct of general intelligence, while the consistency and differences between psychometric and neurometric ontologies represent crucial pieces of knowledge for theory building, clinical diagnostics and treatment.

q-bio.NC↗
arXiv2021

Comparative Validation of Machine Learning Algorithms for Surgical Workflow and Skill Analysis with the HeiChole Benchmark

PURPOSE: Surgical workflow and skill analysis are key technologies for the next generation of cognitive surgical assistance systems. These systems could increase the safety of the operation through context-sensitive warnings and semi-autonomous robotic assistance or improve training of surgeons via data-driven feedback. In surgical workflow analysis up to 91% average precision has been reported for phase recognition on an open data single-center dataset. In this work we investigated the generalizability of phase recognition algorithms in a multi-center setting including more difficult recognition tasks such as surgical action and surgical skill. METHODS: To achieve this goal, a dataset with 33 laparoscopic cholecystectomy videos from three surgical centers with a total operation time of 22 hours was created. Labels included annotation of seven surgical phases with 250 phase transitions, 5514 occurences of four surgical actions, 6980 occurences of 21 surgical instruments from seven instrument categories and 495 skill classifications in five skill dimensions. The dataset was used in the 2019 Endoscopic Vision challenge, sub-challenge for surgical workflow and skill analysis. Here, 12 teams submitted their machine learning algorithms for recognition of phase, action, instrument and/or skill assessment. RESULTS: F1-scores were achieved for phase recognition between 23.9% and 67.7% (n=9 teams), for instrument presence detection between 38.5% and 63.8% (n=8 teams), but for action recognition only between 21.8% and 23.3% (n=5 teams). The average absolute error for skill assessment was 0.78 (n=1 team). CONCLUSION: Surgical workflow and skill analysis are promising technologies to support the surgical team, but are not solved yet, as shown by our comparison of algorithms. This novel benchmark can be used for comparable evaluation and validation of future work.

eess.IV↗
arXiv2020

Battery Asset Management with Cycle Life Prognosis

Battery Asset Management problem determines the minimum cost replacement schedules for each individual asset in a group of battery assets that operate in parallel. Battery cycle life varies under different operating conditions including temperature, depth of discharge, charge rate, etc., and a battery deteriorates due to usage, which cannot be handled by current asset management models. This paper presents battery cycle life prognosis and its integration with parallel asset management to reduce lifecycle cost of the Battery Energy Storage System (BESS). A nonlinear capacity fade model is incorporated in the parallel asset management model to update battery capacity. Parametric studies have been conducted to explore the influence of different model inputs (e.g. usage rate, unit battery capacity, operating condition and periodical demand) for a five-year time horizon. Experiment results verify the reasonableness of this new framework and suggest that the increase in battery lifetime leads to decrease in lifecycle cost.

eess.SY↗