Search

Computed tomography (CT) provides high spatial resolution visualization of 3D structures for scientific and clinical applications. Traditional analytical/iterative CT reconstruction algorithms require hundreds of angular data samplings, a condition that may not be met in practice due to physical and mechanical limitations. Sparse view CT reconstruction has been proposed using constrained optimization and machine learning methods with varying success, less so for ultra-sparse view CT reconstruction with one to two views. Neural radiance field (NeRF) is a powerful tool for reconstructing and rendering 3D natural scenes from sparse views, but its direct application to 3D medical image reconstruction has been minimally successful due to the differences between optical and X-ray photon transportation. Here, we develop a novel TomoGRAF framework incorporating the unique X-ray transportation physics to reconstruct high-quality 3D volumes using ultra-sparse projections without prior. TomoGRAF captures the CT imaging geometry, simulates the X-ray casting and tracing process, and penalizes the difference between simulated and ground truth CT sub-volume during training. We evaluated the performance of TomoGRAF on an unseen dataset of distinct imaging characteristics from the training data and demonstrated a vast leap in performance compared with state-of-the-art deep learning and NeRF methods. TomoGRAF provides the first generalizable solution for image-guided radiotherapy and interventional radiology applications, where only one or a few X-ray views are available, but 3D volumetric information is desired.

In the field of multi-modal language models, the majority of methods are built on an architecture similar to LLaVA. These models use a single-layer ViT feature as a visual prompt, directly feeding it into the language models alongside textual tokens. However, when dealing with long sequences of visual signals or inputs such as videos, the self-attention mechanism of language models can lead to significant computational overhead. Additionally, using single-layer ViT features makes it challenging for large language models to perceive visual signals fully. This paper proposes an efficient multi-modal language model to minimize computational costs while enabling the model to perceive visual signals as comprehensively as possible. Our method primarily includes: (1) employing cross-attention to image-text interaction similar to Flamingo. (2) utilize hierarchical ViT features. (3) introduce the Mixture of Experts (MoE) mechanism to enhance model effectiveness. Our model achieves competitive scores on public multi-modal benchmarks and performs well in tasks such as image captioning and video captioning.

4D head capture aims to generate dynamic topological meshes and corresponding texture maps from videos, which is widely utilized in movies and games for its ability to simulate facial muscle movements and recover dynamic textures in pore-squeezing. The industry often adopts the method involving multi-view stereo and non-rigid alignment. However, this approach is prone to errors and heavily reliant on time-consuming manual processing by artists. To simplify this process, we propose Topo4D, a novel framework for automatic geometry and texture generation, which optimizes densely aligned 4D heads and 8K texture maps directly from calibrated multi-view time-series images. Specifically, we first represent the time-series faces as a set of dynamic 3D Gaussians with fixed topology in which the Gaussian centers are bound to the mesh vertices. Afterward, we perform alternative geometry and texture optimization frame-by-frame for high-quality geometry and texture learning while maintaining temporal topology stability. Finally, we can extract dynamic facial meshes in regular wiring arrangement and high-fidelity textures with pore-level details from the learned Gaussians. Extensive experiments show that our method achieves superior results than the current SOTA face reconstruction methods both in the quality of meshes and textures. Project page: https://xuanchenli.github.io/Topo4D/.

Image-guided mouse irradiation is essential to understand interventions involving radiation prior to human studies. Our objective is to employ Swin UNEt Transformers (Swin UNETR) to segment native micro-CT and contrast-enhanced micro-CT scans and benchmark the results against 3D no-new-Net (nnU-Net). Swin UNETR reformulates mouse organ segmentation as a sequence-to-sequence prediction task, using a hierarchical Swin Transformer encoder to extract features at 5 resolution levels, and connects to a Fully Convolutional Neural Network (FCNN)-based decoder via skip connections. The models were trained and evaluated on open datasets, with data separation based on individual mice. Further evaluation on an external mouse dataset acquired on a different micro-CT with lower kVp and higher imaging noise was also employed to assess model robustness and generalizability. Results indicate that Swin UNETR consistently outperforms nnU-Net and AIMOS in terms of average dice similarity coefficient (DSC) and Hausdorff distance (HD95p), except in two mice of intestine contouring. This superior performance is especially evident in the external dataset, confirming the model's robustness to variations in imaging conditions, including noise and quality, thereby positioning Swin UNETR as a highly generalizable and efficient tool for automated contouring in pre-clinical workflows.

The objective of personalization and stylization in text-to-image is to instruct a pre-trained diffusion model to analyze new concepts introduced by users and incorporate them into expected styles. Recently, parameter-efficient fine-tuning (PEFT) approaches have been widely adopted to address this task and have greatly propelled the development of this field. Despite their popularity, existing efficient fine-tuning methods still struggle to achieve effective personalization and stylization in T2I generation. To address this issue, we propose block-wise Low-Rank Adaptation (LoRA) to perform fine-grained fine-tuning for different blocks of SD, which can generate images faithful to input prompts and target identity and also with desired style. Extensive experiments demonstrate the effectiveness of the proposed method.

Amid efforts to address the ongoing crisis of high costs, high debt burdens, and decreasing confidence in the value of higher education, TICAS [The Institute for College Access & Success] commissioned leading academics to write a series of papers to inform the policy conversation about how to implement effective, equitable, and sustainable solutions to the college affordability crisis. Collectively, the papers outline the current college financing landscape, discuss potential policy options for reducing reliance on debt, and examine specific components that could be addressed as part of a larger federal-state funding partnership to achieve debt-free college for all.

We introduce Lumos, the first end-to-end multimodal question-answering system with text understanding capabilities. At the core of Lumos is a Scene Text Recognition (STR) component that extracts text from first person point-of-view images, the output of which is used to augment input to a Multimodal Large Language Model (MM-LLM). While building Lumos, we encountered numerous challenges related to STR quality, overall latency, and model inference. In this paper, we delve into those challenges, and discuss the system architecture, design choices, and modeling techniques employed to overcome these obstacles. We also provide a comprehensive evaluation for each component, showcasing high quality and efficiency., Comment: Accepted to KDD 2024 (ADS Track)

The fusion of non-Abelian anyons or topological defects is a fundamental operation in measurement-only topological quantum computation. In topological superconductors, this operation amounts to a determination of the shared fermion parity of Majorana zero modes. As a step towards this, we implement a single-shot interferometric measurement of fermion parity in indium arsenide-aluminum heterostructures with a gate-defined nanowire. The interferometer is formed by tunnel-coupling the proximitized nanowire to quantum dots. The nanowire causes a state-dependent shift of these quantum dots' quantum capacitance of up to 1 fF. Our quantum capacitance measurements show flux h/2e-periodic bimodality with a signal-to-noise ratio of 1 in 3.7 $\mu$s at optimal flux values. From the time traces of the quantum capacitance measurements, we extract a dwell time in the two associated states that is longer than 1 ms at in-plane magnetic fields of approximately 2 T. These results are consistent with a measurement of the fermion parity encoded in a pair of Majorana zero modes that are separated by approximately 3 $\mu$m and subjected to a low rate of poisoning by non-equilibrium quasiparticles. The large capacitance shift and long poisoning time enable a parity measurement error probability of 1%., Comment: Added data on a second measurement of device A and a measurement of device B, expanded discussion of a trivial scenario. Refs added, author list updated

Pulmonary nodules may be an early manifestation of lung cancer, the leading cause of cancer-related deaths among both men and women. Numerous studies have established that deep learning methods can yield high-performance levels in the detection of lung nodules in chest X-rays. However, the lack of gold-standard public datasets slows down the progression of the research and prevents benchmarking of methods for this task. To address this, we organized a public research challenge, NODE21, aimed at the detection and generation of lung nodules in chest X-rays. While the detection track assesses state-of-the-art nodule detection systems, the generation track determines the utility of nodule generation algorithms to augment training data and hence improve the performance of the detection systems. This paper summarizes the results of the NODE21 challenge and performs extensive additional experiments to examine the impact of the synthetically generated nodule training images on the detection algorithm performance., Comment: 15 pages, 5 figures

In this work, we focus on exploring explicit fine-grained control of generative facial image editing, all while generating faithful facial appearances and consistent semantic details, which however, is quite challenging and has not been extensively explored, especially under an one-shot scenario. We identify the key challenge as the exploration of disentangled conditional control between high-level semantics and explicit parameters (e.g., 3DMM) in the generation process, and accordingly propose a novel diffusion-based editing framework, named DisControlFace. Specifically, we leverage a Diffusion Autoencoder (Diff-AE) as the semantic reconstruction backbone. To enable explicit face editing, we construct an Exp-FaceNet that is compatible with Diff-AE to generate spatial-wise explicit control conditions based on estimated 3DMM parameters. Different from current diffusion-based editing methods that train the whole conditional generative model from scratch, we freeze the pre-trained weights of the Diff-AE to maintain its semantically deterministic conditioning capability and accordingly propose a random semantic masking (RSM) strategy to effectively achieve an independent training of Exp-FaceNet. This setting endows the model with disentangled face control meanwhile reducing semantic information shift in editing. Our model can be trained using 2D in-the-wild portrait images without requiring 3D or video data and perform robust editing on any new facial image through a simple one-shot fine-tuning. Comprehensive experiments demonstrate that DisControlFace can generate realistic facial images with better editing accuracy and identity preservation over state-of-the-art methods. Project page: https://discontrolface.github.io/

While the COVID-19 pandemic necessitated the short-term use of online courses, colleges' experiences with COVID-era online course delivery may also affect the way that they offer and approach online courses going forward. We draw on interviews with 35 distance education leaders from the California Community Colleges system to provide insights into how the use of online education may change in the system going forward. Leaders predicted that post-pandemic, colleges would increase their online course offerings, and that many instructional innovations to online courses from the pandemic--such as the use of synchronous courses--would persist. They hoped that a more prominent position for online education within the system would be matched by more resources to provide supports for online learning.

Dual enrollment (DE) is one of the fastest growing programs that support the high school-to-college transition. Yet, there is limited empirical evidence about its impact on either students' college application choices or admission outcomes. Using a fuzzy regression discontinuity approach and data from two cohorts of ninth-grade students in one anonymous state, we found that taking DE credits increased the total number of colleges students applied to and the likelihood of applying to any moderately or highly selective in-state four-year institution. Attempting DE credits also increased the total number of in-state four-year colleges a student got admitted to and the probability of being admitted to a highly selective in-state four-year college. Heterogeneous analysis further indicates that the gains were primarily driven by Black students.

The recent realization of a two-site Kitaev chain featuring "poor man's Majorana" states demonstrates a path forward in the field of topological superconductivity. Harnessing the potential of these states for quantum information processing, however, requires increasing their robustness to external perturbations. Here, we form a two-site Kitaev chain using proximitized quantum dots hosting Yu-Shiba-Rusinov states. The strong hybridization between such states and the superconductor enables the creation of poor man's Majorana states with a gap larger than $70 \mathrm{~\mu eV}$. It also greatly reduces the charge dispersion compared to Kitaev chains made with non-proximitized quantum dots. The large gap and reduced sensitivity to charge fluctuations will benefit qubit manipulation and demonstration of non-abelian physics using poor man's Majorana states., Comment: 45 pages, 14 figures

Dual-energy computed tomography (DECT) utilizes separate X-ray energy spectra to improve multi-material decomposition (MMD) for various diagnostic applications. However accurate decomposing more than two types of material remains challenging using conventional methods. Deep learning (DL) methods have shown promise to improve the MMD performance, but typical approaches of conducing DL-MMD in the image domain fail to fully utilize projection information or under iterative setup are computationally inefficient in both training and prediction. In this work, we present a clinical-applicable MMD (>2) framework rFast-MMDNet, operating with raw projection data in non-recursive setup, for breast tissue differentiation. rFast-MMDNet is a two-stage algorithm, including stage-one SinoNet to perform dual energy projection decomposition on tissue sinograms and stage-two FBP-DenoiseNet to perform domain adaptation and image post-processing. rFast-MMDNet was tested on a 2022 DL-Spectral-Challenge breast phantom dataset. The two stages of rFast-MMDNet were evaluated separately and then compared with four noniterative reference methods including a direct inversion method (AA-MMD), an image domain DL method (ID-UNet), AA-MMD/ID-UNet + DenoiseNet and a sinogram domain DL method (Triple-CBCT). Our results show that models trained from information stored in DE transmission domain can yield high-fidelity decomposition of the adipose, calcification, and fibroglandular materials with averaged RMSE, MAE, negative PSNR, and SSIM of 0.004+/-~0, 0.001+/-~0, -45.027+/-~0.542, and 0.002+/-~0 benchmarking to the ground truth, respectively. Training of entire rFast-MMDNet on a 4xRTX A6000 GPU cluster took a day with inference time <1s. All DL methods generally led to more accurate MMD than AA-MMD. rFast-MMDNet outperformed Triple-CBCT, but both are superior to the image-domain based methods., Comment: AAPM 2023 Dl-spectral Challenge Summary

This paper proposes a method for fast scene radiance field reconstruction with strong novel view synthesis performance and convenient scene editing functionality. The key idea is to fully utilize semantic parsing and primitive extraction for constraining and accelerating the radiance field reconstruction process. To fulfill this goal, a primitive-aware hybrid rendering strategy was proposed to enjoy the best of both volumetric and primitive rendering. We further contribute a reconstruction pipeline conducts primitive parsing and radiance field learning iteratively for each input frame which successfully fuses semantic, primitive, and radiance information into a single framework. Extensive evaluations demonstrate the fast reconstruction ability, high rendering quality, and convenient editing functionality of our method., Comment: Accepted to ICCV 2023; Project page: https://oceanying.github.io/PARF/

Dynamic magnetic resonance imaging (DMRI) is an effective imaging tool for diagnosis tasks that require motion tracking of a certain anatomy. To speed up DMRI acquisition, k-space measurements are commonly undersampled along spatial or spatial-temporal domains. The difficulty of recovering useful information increases with increasing undersampling ratios. Compress sensing was invented for this purpose and has become the most popular method until deep learning (DL) based DMRI reconstruction methods emerged in the past decade. Nevertheless, existing DL networks are still limited in long-range sequential dependency understanding and computational efficiency and are not fully automated. Considering the success of Transformers positional embedding and "swin window" self-attention mechanism in the vision community, especially natural video understanding, we hereby propose a novel architecture named Reconstruction Swin Transformer (RST) for 4D MRI. RST inherits the backbone design of the Video Swin Transformer with a novel reconstruction head introduced to restore pixel-wise intensity. A convolution network called SADXNet is used for rapid initialization of 2D MR frames before RST learning to effectively reduce the model complexity, GPU hardware demand, and training time. Experimental results in the cardiac 4D MR dataset further substantiate the superiority of RST, achieving the lowest RMSE of 0.0286 +/- 0.0199 and 1 - SSIM of 0.0872 +/- 0.0783 on 9 times accelerated validation sequences., Comment: MICCAI 2023 Workshop

Accurate depth estimation under out-of-distribution (OoD) scenarios, such as adverse weather conditions, sensor failure, and noise contamination, is desirable for safety-critical applications. Existing depth estimation systems, however, suffer inevitably from real-world corruptions and perturbations and are struggled to provide reliable depth predictions under such cases. In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation. This challenge was developed based on the newly established KITTI-C and NYUDepth2-C benchmarks. We hosted two stand-alone tracks, with an emphasis on robust self-supervised and robust fully-supervised depth estimation, respectively. Out of more than two hundred participants, nine unique and top-performing solutions have appeared, with novel designs ranging from the following aspects: spatial- and frequency-domain augmentations, masked image modeling, image restoration and super-resolution, adversarial training, diffusion-based noise suppression, vision-language pre-training, learned model ensembling, and hierarchical feature enhancement. Extensive experimental analyses along with insightful observations are drawn to better understand the rationale behind each design. We hope this challenge could lay a solid foundation for future research on robust and reliable depth estimation and beyond. The datasets, competition toolkit, workshop recordings, and source code from the winning teams are publicly available on the challenge website., Comment: Technical Report; 65 pages, 34 figures, 24 tables; Code at https://github.com/ldkong1205/RoboDepth

We introduce a novel dataset consisting of images depicting pink eggs that have been identified as Pomacea canaliculata eggs, accompanied by corresponding bounding box annotations. The purpose of this dataset is to aid researchers in the analysis of the spread of Pomacea canaliculata species by utilizing deep learning techniques, as well as supporting other investigative pursuits that require visual data pertaining to the eggs of Pomacea canaliculata. It is worth noting, however, that the identity of the eggs in question is not definitively established, as other species within the same taxonomic family have been observed to lay similar-looking eggs in regions of the Americas. Therefore, a crucial prerequisite to any decision regarding the elimination of these eggs would be to establish with certainty whether they are exclusively attributable to invasive Pomacea canaliculata or if other species are also involved. The dataset is available at https://www.kaggle.com/datasets/deeshenzhen/pinkeggs

Long-tailed multi-label visual recognition (LTML) task is a highly challenging task due to the label co-occurrence and imbalanced data distribution. In this work, we propose a unified framework for LTML, namely prompt tuning with class-specific embedding loss (LMPT), capturing the semantic feature interactions between categories by combining text and image modality data and improving the performance synchronously on both head and tail classes. Specifically, LMPT introduces the embedding loss function with class-aware soft margin and re-weighting to learn class-specific contexts with the benefit of textual descriptions (captions), which could help establish semantic relationships between classes, especially between the head and tail classes. Furthermore, taking into account the class imbalance, the distribution-balanced loss is adopted as the classification loss function to further improve the performance on the tail classes without compromising head classes. Extensive experiments are conducted on VOC-LT and COCO-LT datasets, which demonstrates that our method significantly surpasses the previous state-of-the-art methods and zero-shot CLIP in LTML. Our codes are fully public at https://github.com/richard-peng-xia/LMPT., Comment: Accepted by 3rd Workshop on Advances in Language and Vision Research (ALVR) @ ACL 2024

Deep neural network (DNN) partition is a research problem that involves splitting a DNN into multiple parts and offloading them to specific locations. Because of the recent advancement in multi-access edge computing and edge intelligence, DNN partition has been considered as a powerful tool for improving DNN inference performance when the computing resources of edge and end devices are limited and the remote transmission of data from these devices to clouds is costly. This paper provides a comprehensive survey on the recent advances and challenges in DNN partition approaches over the cloud, edge, and end devices based on a detailed literature collection. We review how DNN partition works in various application scenarios, and provide a unified mathematical model of the DNN partition problem. We developed a five-dimensional classification framework for DNN partition approaches, consisting of deployment locations, partition granularity, partition constraints, optimization objectives, and optimization algorithms. Each existing DNN partition approache can be perfectly defined in this framework by instantiating each dimension into specific values. In addition, we suggest a set of metrics for comparing and evaluating the DNN partition approaches. Based on this, we identify and discuss research challenges that have not yet been investigated or fully addressed. We hope that this work helps DNN partition researchers by highlighting significant future research directions in this domain.

Suppression of thoracic bone shadows on chest X-rays (CXRs) has been indicated to improve the diagnosis of pulmonary disease. Previous approaches can be categorized as unsupervised physical and supervised deep learning models. Nevertheless, with physical models able to preserve morphological details but at the cost of extremely long processing time, existing DL methods face challenges of gathering sufficient/qualitative ground truth (GT) for robust training, thus leading to failure in maintaining clinically acceptable false positive rates. We hereby propose a generalizable yet efficient workflow of two stages: (1) training pairs generation with GT bone shadows eliminated in by a physical model in spatially transformed gradient fields. (2) fully supervised image denoising network training on stage-one datasets for fast rib removal on incoming CXRs. For step two, we designed a densely connected network called SADXNet, combined with peak signal to noise ratio and multi-scale structure similarity index measure objective minimization to suppress bony structures. The SADXNet organizes spatial filters in U shape (e.g., X=7; filters = 16, 64, 256, 512, 256, 64, 16) and preserves the feature map dimension throughout the network flow. Visually, SADXNet can suppress the rib edge and that near the lung wall/vertebra without jeopardizing the vessel/abnormality conspicuity. Quantitively, it achieves RMSE of ~0 during testing with one prediction taking <1s. Downstream tasks including lung nodule detection as well as common lung disease classification and localization are used to evaluate our proposed rib suppression mechanism. We observed 3.23% and 6.62% area under the curve (AUC) increase as well as 203 and 385 absolute false positive decrease for lung nodule detection and common lung disease localization, separately.

A semiconductor nanowire brought in proximity to a superconductor can form discrete, particle-hole symmetric states, known as Andreev bound states (ABSs). An ABS can be found in its ground or excited states of different spin and parity, such as a spin-zero singlet state with an even number of electrons or a spin-1/2 doublet state with an odd number of electrons. Considering the difference between spin of the even and odd states, spin-filtered measurements have the potential to reveal the underlying ground state. To directly measure the spin of single-electron excitations, we probe an ABS using a spin-polarized quantum dot that acts as a bipolar spin filter, in combination with a non-polarized tunnel junction in a three-terminal circuit. We observe a spin-polarized excitation spectrum of the ABS, which in some cases is fully spin-polarized, despite the presence of strong spin-orbit interaction in the InSb nanowires. In addition, decoupling the hybrid from the normal lead blocks the ABS relaxation resulting in a current blockade where the ABS is trapped in an excited state. Spin-polarized spectroscopy of hybrid nanowire devices, as demonstrated here, is proposed as an experimental tool to support the observation of topological superconductivity.

A short superconducting segment can couple attached quantum dots via elastic co-tunneling (ECT) and crossed Andreev reflection (CAR). Such coupled quantum dots can host Majorana bound states provided that the ratio between CAR and ECT can be controlled. Metallic superconductors have so far been shown to mediate such tunneling phenomena, albeit with limited tunability. Here we show that Andreev bound states formed in semiconductor-superconductor heterostructures can mediate CAR and ECT over mesoscopic length scales. Andreev bound states possess both an electron and a hole component, giving rise to an intricate interference phenomenon that allows us to tune the ratio between CAR and ECT deterministically. We further show that the combination of intrinsic spin-orbit coupling in InSb nanowires and an applied magnetic field provides another efficient knob to tune the ratio between ECT and CAR and optimize the amount of coupling between neighboring quantum dots.