arXiv subjects

Zihan Li

Publications and source records attributed to Zihan Li.

At least 91 records · Page 5Linked to original sources

arXiv2024

Enhance the Image: Super Resolution using Artificial Intelligence in MRI

This chapter provides an overview of deep learning techniques for improving the spatial resolution of MRI, ranging from convolutional neural networks, generative adversarial networks, to more advanced models including transformers, diffusion models, and implicit neural representations. Our exploration extends beyond the methodologies to scrutinize the impact of super-resolved images on clinical and neuroscientific assessments. We also cover various practical topics such as network architectures, image evaluation metrics, network loss functions, and training data specifics, including downsampling methods for simulating low-resolution images and dataset selection. Finally, we discuss existing challenges and potential future directions regarding the feasibility and reliability of deep learning-based MRI super-resolution, with the aim to facilitate its wider adoption to benefit various clinical and neuroscientific applications.

cs.CV↗

arXiv2024

Rethinking Abdominal Organ Segmentation (RAOS) in the clinical scenario: A robustness evaluation benchmark with challenging cases

Deep learning has enabled great strides in abdominal multi-organ segmentation, even surpassing junior oncologists on common cases or organs. However, robustness on corner cases and complex organs remains a challenging open problem for clinical adoption. To investigate model robustness, we collected and annotated the RAOS dataset comprising 413 CT scans ($\sim$80k 2D images, $\sim$8k 3D organ annotations) from 413 patients each with 17 (female) or 19 (male) labelled organs, manually delineated by oncologists. We grouped scans based on clinical information into 1) diagnosis/radiotherapy (317 volumes), 2) partial excision without the whole organ missing (22 volumes), and 3) excision with the whole organ missing (74 volumes). RAOS provides a potential benchmark for evaluating model robustness including organ hallucination. It also includes some organs that can be very hard to access on public datasets like the rectum, colon, intestine, prostate and seminal vesicles. We benchmarked several state-of-the-art methods in these three clinical groups to evaluate performance and robustness. We also assessed cross-generalization between RAOS and three public datasets. This dataset and comprehensive analysis establish a potential baseline for future robustness research: \url{https://github.com/Luoxd1996/RAOS}.

eess.IV↗

arXiv2024

nnSAM: Plug-and-play Segment Anything Model Improves nnUNet Performance

Automatic segmentation of medical images is crucial in modern clinical workflows. The Segment Anything Model (SAM) has emerged as a versatile tool for image segmentation without specific domain training, but it requires human prompts and may have limitations in specific domains. Traditional models like nnUNet perform automatic segmentation during inference and are effective in specific domains but need extensive domain-specific training. To combine the strengths of foundational and domain-specific models, we propose nnSAM, integrating SAM's robust feature extraction with nnUNet's automatic configuration to enhance segmentation accuracy on small datasets. Our nnSAM model optimizes two main approaches: leveraging SAM's feature extraction and nnUNet's domain-specific adaptation, and incorporating a boundary shape supervision loss function based on level set functions and curvature calculations to learn anatomical shape priors from limited data. We evaluated nnSAM on four segmentation tasks: brain white matter, liver, lung, and heart segmentation. Our method outperformed others, achieving the highest DICE score of 82.77% and the lowest ASD of 1.14 mm in brain white matter segmentation with 20 training samples, compared to nnUNet's DICE score of 79.25% and ASD of 1.36 mm. A sample size study highlighted nnSAM's advantage with fewer training samples. Our results demonstrate significant improvements in segmentation performance with nnSAM, showcasing its potential for small-sample learning in medical image segmentation.

cs.CV↗

arXiv2024

Regret Bounds for Noise-Free Cascaded Kernelized Bandits

We consider optimizing a function network in the noise-free grey-box setting with RKHS function classes, where the exact intermediate results are observable. We assume that the structure of the network is known (but not the underlying functions comprising it), and we study three types of structures: (1) chain: a cascade of scalar-valued functions, (2) multi-output chain: a cascade of vector-valued functions, and (3) feed-forward network: a fully connected feed-forward network of scalar-valued functions. We propose a sequential upper confidence bound based algorithm GPN-UCB along with a general theoretical upper bound on the cumulative regret. In addition, we propose a non-adaptive sampling based method along with its theoretical upper bound on the simple regret for the Matérn kernel. We also provide algorithm-independent lower bounds on the simple regret and cumulative regret. Our regret bounds for GPN-UCB have the same dependence on the time horizon as the best known in the vanilla black-box setting, as well as near-optimal dependencies on other parameters (e.g., RKHS norm and network length).

stat.ML↗

arXiv2024

Complexity of Round-Robin Allocation with Potentially Noisy Queries

We study the complexity of a fundamental algorithm for fairly allocating indivisible items, the round-robin algorithm. For $n$ agents and $m$ items, we show that the algorithm can be implemented in time $O(nm\log(m/n))$ in the worst case. If the agents' preferences are uniformly random, we establish an improved (expected) running time of $O(nm + m\log m)$. On the other hand, assuming comparison queries between items, we prove that $Ω(nm + m\log m)$ queries are necessary to implement the algorithm, even when randomization is allowed. We also derive bounds in noise models where the answers to queries are incorrect with some probability. Our proofs involve novel applications of tools from multi-armed bandit, information theory, as well as posets and linear extensions.

cs.GT↗

arXiv2024

Symmetric Entropy Regions of Degrees Six and Seven

In this paper, we classify all G-symmetric almost entropic regions according to their Shannon-tightness, that is, whether they can be fully characterized by Shannon-type inequalities, where G is a permutation group of degree 6 or 7.

cs.IT↗

arXiv2024

Hydrogen-free low-temperature silica for next generation integrated photonics

The advances in novel low-loss "on insulator" integrated photonics platforms beyond silicon, such as thin-film LiNbO3, LiTaO3, GaP and BaTiO3 have demonstrated major potential across a wide range of applications, due to their unique electro-optical or nonlinear optical properties. This has heralded novel devices, ranging from low-voltage and high-speed modulators to parametric amplifiers. For such photonic integrated circuits, a low-loss SiO2 cladding layer is a key element, serving as a passivation layer for the waveguides and enabling efficient fiber-to-chip coupling. However, numerous novel ferroelectric or III-V "on insulator" platforms have low tolerances for process temperature. This prohibits using high-temperature anneals to remove hydrogen, a common impurity that is inherent to ordinary chemical vapor deposited SiO2 and causes significant optical loss in the near infrared. Here, we satisfy the dichotomy of a low-loss wafer scale manufactured SiO2 cladding and low processing temperature. Inspired by the manufacturing of optical fibers, we introduce a hydrogen-free, low-loss SiO2 cladding that is deposited at low temperatures (300 degrees Celsius) by using SiCl4 and O2 as precursors in inductively coupled plasma-enhanced chemical vapor deposition (ICPCVD). By replacing hydrogenous silicon precursors (e.g. SiH4) with SiCl4, the deposited film is inherently free from residual hydrogen. The process temperature is compatible with the "on insulator" platforms and CMOS electronic integrated circuits. We demonstrate a wide low-loss window that covers all telecommunication bands from 1260 nm to 1625 nm. We achieve a < 2.5 dB/m waveguide loss at 1550 nm, comparable with 1200 degree Celsius annealed films. Our SiCl4 process provides a key future cladding for all recently emerged "on-insulator" photonics platforms, that is low cost, scalable in manufacturing, and directly foundry compatible.

physics.optics↗

arXiv2024

Piecing Together Clues: A Benchmark for Evaluating the Detective Skills of Large Language Models

Detectives frequently engage in information detection and reasoning simultaneously when making decisions across various cases, especially when confronted with a vast amount of information. With the rapid development of large language models~(LLMs), evaluating how these models identify key information and reason to solve questions becomes increasingly relevant. We introduces the DetectBench, a reading comprehension dataset designed to assess a model's ability to jointly ability in key information detection and multi-hop reasoning when facing complex and implicit information. The DetectBench comprises 3,928 questions, each paired with a paragraph averaging 190 tokens in length. To enhance model's detective skills, we propose the Detective Thinking Framework. These methods encourage models to identify all possible clues within the context before reasoning. Our experiments reveal that existing models perform poorly in both information detection and multi-hop reasoning. However, the Detective Thinking Framework approach alleviates this issue.

cs.CL↗

arXiv2024

Single-Shot Single-Beam Coherent Raman Scattering Thermometry Based on Air Lasing

Thermometric techniques with high accuracy, fast response speed and ease of implementation are desirable for the study of dynamic combustion environments, transient reacting flows, and non-equilibrium plasmas. Herein, single-shot single-beam coherent Raman scattering (SS-CRS) thermometry is developed, for the first time to our knowledge, by using air lasing as a probe. It's proved that the air-lasing-assisted CRS signal has a high signal-to-noise ratio enabling single-shot measurements at a 1 kHz repetition rate. The SS-CRS thermometry consistently exhibits precision better than 2% at different temperatures, but the inaccuracy grows with the increase in temperature. The high detection precision, 1 kHz acquisition rate and easy-to-implement single-beam scheme are achieved thanks to the unique temporal, spectral and spatial characteristics of air lasing. This work opens a novel avenue for high-speed CRS thermometry, holding tremendous potential for fast diagnostics of transient reacting flows and plasmas.

physics.optics↗

arXiv2024

Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation

New Natural Langauge Process~(NLP) benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present Xiezhi, the most comprehensive evaluation suite designed to assess holistic domain knowledge. Xiezhi comprises multiple-choice questions across 516 diverse disciplines ranging from 13 different subjects with 249,587 questions and accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results indicate that LLMs exceed average performance of humans in science, engineering, agronomy, medicine, and art, but fall short in economics, jurisprudence, pedagogy, literature, history, and management. We anticipate Xiezhi will help analyze important strengths and shortcomings of LLMs, and the benchmark is released in~\url{https://github.com/MikeGu721/XiezhiBenchmark}.

cs.CL↗

arXiv2024

ScribFormer: Transformer Makes CNN Work Better for Scribble-based Medical Image Segmentation

Most recent scribble-supervised segmentation methods commonly adopt a CNN framework with an encoder-decoder architecture. Despite its multiple benefits, this framework generally can only capture small-range feature dependency for the convolutional layer with the local receptive field, which makes it difficult to learn global shape information from the limited information provided by scribble annotations. To address this issue, this paper proposes a new CNN-Transformer hybrid solution for scribble-supervised medical image segmentation called ScribFormer. The proposed ScribFormer model has a triple-branch structure, i.e., the hybrid of a CNN branch, a Transformer branch, and an attention-guided class activation map (ACAM) branch. Specifically, the CNN branch collaborates with the Transformer branch to fuse the local features learned from CNN with the global representations obtained from Transformer, which can effectively overcome limitations of existing scribble-supervised segmentation methods. Furthermore, the ACAM branch assists in unifying the shallow convolution features and the deep convolution features to improve model's performance further. Extensive experiments on two public datasets and one private dataset show that our ScribFormer has superior performance over the state-of-the-art scribble-supervised segmentation methods, and achieves even better results than the fully-supervised segmentation methods. The code is released at https://github.com/HUANGLIZI/ScribFormer.

cs.CV↗

arXiv2024

Can Large Language Models Understand Real-World Complex Instructions?

Large language models (LLMs) can understand human instructions, showing their potential for pragmatic applications beyond traditional NLP tasks. However, they still struggle with complex instructions, which can be either complex task descriptions that require multiple tasks and constraints, or complex input that contains long context, noise, heterogeneous information and multi-turn format. Due to these features, LLMs often ignore semantic constraints from task descriptions, generate incorrect formats, violate length or sample count constraints, and be unfaithful to the input text. Existing benchmarks are insufficient to assess LLMs' ability to understand complex instructions, as they are close-ended and simple. To bridge this gap, we propose CELLO, a benchmark for evaluating LLMs' ability to follow complex instructions systematically. We design eight features for complex instructions and construct a comprehensive evaluation dataset from real-world scenarios. We also establish four criteria and develop corresponding metrics, as current ones are inadequate, biased or too strict and coarse-grained. We compare the performance of representative Chinese-oriented and English-oriented models in following complex instructions through extensive experiments. Resources of CELLO are publicly available at https://github.com/Abbey4799/CELLO.

cs.CL↗

arXiv2023

Implicit Neural Representation for Cooperative Low-light Image Enhancement

The following three factors restrict the application of existing low-light image enhancement methods: unpredictable brightness degradation and noise, inherent gap between metric-favorable and visual-friendly versions, and the limited paired training data. To address these limitations, we propose an implicit Neural Representation method for Cooperative low-light image enhancement, dubbed NeRCo. It robustly recovers perceptual-friendly results in an unsupervised manner. Concretely, NeRCo unifies the diverse degradation factors of real-world scenes with a controllable fitting function, leading to better robustness. In addition, for the output results, we introduce semantic-orientated supervision with priors from the pre-trained vision-language model. Instead of merely following reference images, it encourages results to meet subjective expectations, finding more visual-friendly solutions. Further, to ease the reliance on paired data and reduce solution space, we develop a dual-closed-loop constrained enhancement module. It is trained cooperatively with other affiliated modules in a self-supervised manner. Finally, extensive experiments demonstrate the robustness and superior effectiveness of our proposed NeRCo. Our code is available at https://github.com/Ysz2022/NeRCo.

cs.CV↗

arXiv2023

Domain Mastery Benchmark: An Ever-Updating Benchmark for Evaluating Holistic Domain Knowledge of Large Language Model--A Preliminary Release

Domain knowledge refers to the in-depth understanding, expertise, and familiarity with a specific subject, industry, field, or area of special interest. The existing benchmarks are all lack of an overall design for domain knowledge evaluation. Holding the belief that the real ability of domain language understanding can only be fairly evaluated by an comprehensive and in-depth benchmark, we introduces the Domma, a Domain Mastery Benchmark. DomMa targets at testing Large Language Models (LLMs) on their domain knowledge understanding, it features extensive domain coverage, large data volume, and a continually updated data set based on Chinese 112 first-level subject classifications. DomMa consist of 100,000 questions in both Chinese and English sourced from graduate entrance examinations and undergraduate exams in Chinese college. We have also propose designs to make benchmark and evaluation process more suitable to LLMs.

cs.CL↗

arXiv2023

ScribbleVC: Scribble-supervised Medical Image Segmentation with Vision-Class Embedding

Medical image segmentation plays a critical role in clinical decision-making, treatment planning, and disease monitoring. However, accurate segmentation of medical images is challenging due to several factors, such as the lack of high-quality annotation, imaging noise, and anatomical differences across patients. In addition, there is still a considerable gap in performance between the existing label-efficient methods and fully-supervised methods. To address the above challenges, we propose ScribbleVC, a novel framework for scribble-supervised medical image segmentation that leverages vision and class embeddings via the multimodal information enhancement mechanism. In addition, ScribbleVC uniformly utilizes the CNN features and Transformer features to achieve better visual feature extraction. The proposed method combines a scribble-based approach with a segmentation network and a class-embedding module to produce accurate segmentation masks. We evaluate ScribbleVC on three benchmark datasets and compare it with state-of-the-art methods. The experimental results demonstrate that our method outperforms existing approaches in terms of accuracy, robustness, and efficiency. The datasets and code are released on GitHub.

cs.CV↗

arXiv2023

SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation

Recent advancements in large-scale Vision Transformers have made significant strides in improving pre-trained models for medical image segmentation. However, these methods face a notable challenge in acquiring a substantial amount of pre-training data, particularly within the medical field. To address this limitation, we present Masked Multi-view with Swin Transformers (SwinMM), a novel multi-view pipeline for enabling accurate and data-efficient self-supervised medical image analysis. Our strategy harnesses the potential of multi-view information by incorporating two principal components. In the pre-training phase, we deploy a masked multi-view encoder devised to concurrently train masked multi-view observations through a range of diverse proxy tasks. These tasks span image reconstruction, rotation, contrastive learning, and a novel task that employs a mutual learning paradigm. This new task capitalizes on the consistency between predictions from various perspectives, enabling the extraction of hidden multi-view information from 3D medical data. In the fine-tuning stage, a cross-view decoder is developed to aggregate the multi-view information through a cross-attention block. Compared with the previous state-of-the-art self-supervised learning method Swin UNETR, SwinMM demonstrates a notable advantage on several medical image segmentation tasks. It allows for a smooth integration of multi-view information, significantly boosting both the accuracy and data-efficiency of the model. Code and models are available at https://github.com/UCSC-VLAA/SwinMM/.

cs.CV↗

arXiv2023

Lithium tantalate electro-optical photonic integrated circuits for high volume manufacturing

Photonic integrated circuits based on Lithium Niobate have demonstrated the vast capabilities afforded by material with a high Pockels coefficient, allowing linear and high-speed modulators operating at CMOS voltage levels for applications ranging from data-center communications and photonic accelerators for AI. However despite major progress, the industrial adoption of this technology is compounded by the high cost per wafer. Here we overcome this challenge and demonstrate a photonic platform that satisfies the dichotomy of allowing scalable manufacturing at low cost, while at the same time exhibiting equal, and superior properties to those of Lithium Niobate. We demonstrate that it is possible to manufacture low loss photonic integrated circuits using Lithium Tantalate, a material that is already commercially adopted for acoustic filters in 5G and 6G. We show that LiTaO3 posses equally attractive optical properties and can be etched with high precision and negligible residues using DUV lithography, diamond like carbon (DLC) as a hard mask and alkaline wet etching. Using this approach we demonstrate microresonators with an intrinsic cavity linewidth of 26.8 MHz, corresponding to a linear loss of 5.6 dB/m and demonstrate a Mach Zehnder modulator with Vpi L = 4.2 V cm half-wave voltage length product. In comparison to Lithium Niobate, the photonic integrated circuits based on LiTaO3 exhibit a much lower birefringence, allowing high-density circuits and broadband operation over all telecommunication bands (O to L band), exhibit higher photorefractive damage threshold, and lower microwave loss tangent. Moreover, we show that the platform supports generation of soliton microcombs in X-Cut LiTaO3 racetrack microresonator with electronically detectable repetition rate, i.e. 30.1 GHz.

physics.optics↗

arXiv2023

LViT: Language meets Vision Transformer in Medical Image Segmentation

Deep learning has been widely used in medical image segmentation and other aspects. However, the performance of existing medical image segmentation models has been limited by the challenge of obtaining sufficient high-quality labeled data due to the prohibitive data annotation cost. To alleviate this limitation, we propose a new text-augmented medical image segmentation model LViT (Language meets Vision Transformer). In our LViT model, medical text annotation is incorporated to compensate for the quality deficiency in image data. In addition, the text information can guide to generate pseudo labels of improved quality in the semi-supervised learning. We also propose an Exponential Pseudo label Iteration mechanism (EPI) to help the Pixel-Level Attention Module (PLAM) preserve local image features in semi-supervised LViT setting. In our model, LV (Language-Vision) loss is designed to supervise the training of unlabeled images using text information directly. For evaluation, we construct three multimodal medical segmentation datasets (image + text) containing X-rays and CT images. Experimental results show that our proposed LViT has superior segmentation performance in both fully-supervised and semi-supervised setting. The code and datasets are available at https://github.com/HUANGLIZI/LViT.

cs.CV↗