arXiv subjects

Zhihao Chen

Publications and source records attributed to Zhihao Chen.

At least 55 records · Page 3Linked to original sources

arXiv2024

Features Reconstruction Disentanglement Cloth-Changing Person Re-Identification

Cloth-changing person re-identification (CC-ReID) aims to retrieve specific pedestrians in a cloth-changing scenario. Its main challenge is to disentangle the clothing-related and clothing-unrelated features. Most existing approaches force the model to learn clothing-unrelated features by changing the color of the clothes. However, due to the lack of ground truth, these methods inevitably introduce noise, which destroys the discriminative features and leads to an uncontrollable disentanglement process. In this paper, we propose a new person re-identification network called features reconstruction disentanglement ReID (FRD-ReID), which can controllably decouple the clothing-unrelated and clothing-related features. Specifically, we first introduce the human parsing mask as the ground truth of the reconstruction process. At the same time, we propose the far away attention (FAA) mechanism and the person contour attention (PCA) mechanism for clothing-unrelated features and pedestrian contour features to improve the feature reconstruction efficiency. In the testing phase, we directly discard the clothing-related features for inference,which leads to a controllable disentanglement process. We conducted extensive experiments on the PRCC, LTCC, and Vc-Clothes datasets and demonstrated that our method outperforms existing state-of-the-art methods.

cs.CV↗

arXiv2024

HiDiff: Hybrid Diffusion Framework for Medical Image Segmentation

Medical image segmentation has been significantly advanced with the rapid development of deep learning (DL) techniques. Existing DL-based segmentation models are typically discriminative; i.e., they aim to learn a mapping from the input image to segmentation masks. However, these discriminative methods neglect the underlying data distribution and intrinsic class characteristics, suffering from unstable feature space. In this work, we propose to complement discriminative segmentation methods with the knowledge of underlying data distribution from generative models. To that end, we propose a novel hybrid diffusion framework for medical image segmentation, termed HiDiff, which can synergize the strengths of existing discriminative segmentation models and new generative diffusion models. HiDiff comprises two key components: discriminative segmentor and diffusion refiner. First, we utilize any conventional trained segmentation models as discriminative segmentor, which can provide a segmentation mask prior for diffusion refiner. Second, we propose a novel binary Bernoulli diffusion model (BBDM) as the diffusion refiner, which can effectively, efficiently, and interactively refine the segmentation mask by modeling the underlying data distribution. Third, we train the segmentor and BBDM in an alternate-collaborative manner to mutually boost each other. Extensive experimental results on abdomen organ, brain tumor, polyps, and retinal vessels segmentation datasets, covering four widely-used modalities, demonstrate the superior performance of HiDiff over existing medical segmentation algorithms, including the state-of-the-art transformer- and diffusion-based ones. In addition, HiDiff excels at segmenting small objects and generalizing to new datasets. Source codes are made available at https://github.com/takimailto/HiDiff.

cs.CV↗

arXiv2024

Reliable Source Approximation: Source-Free Unsupervised Domain Adaptation for Vestibular Schwannoma MRI Segmentation

Source-Free Unsupervised Domain Adaptation (SFUDA) has recently become a focus in the medical image domain adaptation, as it only utilizes the source model and does not require annotated target data. However, current SFUDA approaches cannot tackle the complex segmentation task across different MRI sequences, such as the vestibular schwannoma segmentation. To address this problem, we proposed Reliable Source Approximation (RSA), which can generate source-like and structure-preserved images from the target domain for updating model parameters and adapting domain shifts. Specifically, RSA deploys a conditional diffusion model to generate multiple source-like images under the guidance of varying edges of one target image. An uncertainty estimation module is then introduced to predict and refine reliable pseudo labels of generated images, and the prediction consistency is developed to select the most reliable generations. Subsequently, all reliable generated images and their pseudo labels are utilized to update the model. Our RSA is validated on vestibular schwannoma segmentation across multi-modality MRI. The experimental results demonstrate that RSA consistently improves domain adaptation performance over other state-of-the-art SFUDA methods. Code is available at https://github.com/zenghy96/Reliable-Source-Approximation.

eess.IV↗

arXiv2024

MambaUIE&SR: Unraveling the Ocean's Secrets with Only 2.8 GFLOPs

Underwater Image Enhancement (UIE) techniques aim to address the problem of underwater image degradation due to light absorption and scattering. In recent years, both Convolution Neural Network (CNN)-based and Transformer-based methods have been widely explored. In addition, combining CNN and Transformer can effectively combine global and local information for enhancement. However, this approach is still affected by the secondary complexity of the Transformer and cannot maximize the performance. Recently, the state-space model (SSM) based architecture Mamba has been proposed, which excels in modeling long distances while maintaining linear complexity. This paper explores the potential of this SSM-based model for UIE from both efficiency and effectiveness perspectives. However, the performance of directly applying Mamba is poor because local fine-grained features, which are crucial for image enhancement, cannot be fully utilized. Specifically, we customize the MambaUIE architecture for efficient UIE. Specifically, we introduce visual state space (VSS) blocks to capture global contextual information at the macro level while mining local information at the micro level. Also, for these two kinds of information, we propose a Dynamic Interaction Block (DIB) and Spatial feed-forward Network (SGFN) for intra-block feature aggregation. MambaUIE is able to efficiently synthesize global and local information and maintains a very small number of parameters with high accuracy. Experiments on UIEB datasets show that our method reduces GFLOPs by 67.4% (2.715G) relative to the SOTA method. To the best of our knowledge, this is the first UIE model constructed based on SSM that breaks the limitation of FLOPs on accuracy in UIE. The official repository of MambaUIE at https://github.com/1024AILab/MambaUIE.

eess.IV↗

arXiv2024

FLDM-VTON: Faithful Latent Diffusion Model for Virtual Try-on

Despite their impressive generative performance, latent diffusion model-based virtual try-on (VTON) methods lack faithfulness to crucial details of the clothes, such as style, pattern, and text. To alleviate these issues caused by the diffusion stochastic nature and latent supervision, we propose a novel Faithful Latent Diffusion Model for VTON, termed FLDM-VTON. FLDM-VTON improves the conventional latent diffusion process in three major aspects. First, we propose incorporating warped clothes as both the starting point and local condition, supplying the model with faithful clothes priors. Second, we introduce a novel clothes flattening network to constrain generated try-on images, providing clothes-consistent faithful supervision. Third, we devise a clothes-posterior sampling for faithful inference, further enhancing the model performance over conventional clothes-agnostic Gaussian sampling. Extensive experimental results on the benchmark VITON-HD and Dress Code datasets demonstrate that our FLDM-VTON outperforms state-of-the-art baselines and is able to generate photo-realistic try-on images with faithful clothing details.

cs.CV↗

arXiv2024

Beam Shaping Based on Axisymmetric Aspheric Mirrors

Flat-top beam, known for its ability to generate a consistently even irradiation area, holds vast utility in many fields of scientific and industrial applications. In this paper, a reflective laser beam shaping method based on two axisymmetric aspheric mirrors (AAMs), a polarizing beam splitter (PBS) and two quarter wave plates (QWPs) is proposed to transform Gaussian beam into flat-top beam. Compared to alternative beam shaping methods, the method using AAMs demonstrates distinct advantages on notably high energy efficiency and unique capability to generate parallel beams. Thanks to its relative simplicities of design, manufacture and tunability, AAMs-shaping further enhances its appeal in applied research scenarios.

physics.optics↗

arXiv2024

Topicwise Separable Sentence Retrieval for Medical Report Generation

Automated radiology reporting holds immense clinical potential in alleviating the burdensome workload of radiologists and mitigating diagnostic bias. Recently, retrieval-based report generation methods have garnered increasing attention due to their inherent advantages in terms of the quality and consistency of generated reports. However, due to the long-tail distribution of the training data, these models tend to learn frequently occurring sentences and topics, overlooking the rare topics. Regrettably, in many cases, the descriptions of rare topics often indicate critical findings that should be mentioned in the report. To address this problem, we introduce a Topicwise Separable Sentence Retrieval (Teaser) for medical report generation. To ensure comprehensive learning of both common and rare topics, we categorize queries into common and rare types to learn differentiated topics, and then propose Topic Contrastive Loss to effectively align topics and queries in the latent space. Moreover, we integrate an Abstractor module following the extraction of visual features, which aids the topic decoder in gaining a deeper understanding of the visual observational intent. Experiments on the MIMIC-CXR and IU X-ray datasets demonstrate that Teaser surpasses state-of-the-art models, while also validating its capability to effectively represent rare topics and establish more dependable correspondences between queries and topics.

cs.CV↗

arXiv2024

Part-Attention Based Model Make Occluded Person Re-Identification Stronger

The goal of occluded person re-identification (ReID) is to retrieve specific pedestrians in occluded situations. However, occluded person ReID still suffers from background clutter and low-quality local feature representations, which limits model performance. In our research, we introduce a new framework called PAB-ReID, which is a novel ReID model incorporating part-attention mechanisms to tackle the aforementioned issues effectively. Firstly, we introduce the human parsing label to guide the generation of more accurate human part attention maps. In addition, we propose a fine-grained feature focuser for generating fine-grained human local feature representations while suppressing background interference. Moreover, We also design a part triplet loss to supervise the learning of human local features, which optimizes intra/inter-class distance. We conducted extensive experiments on specialized occlusion and regular ReID datasets, showcasing that our approach outperforms the existing state-of-the-art methods.

cs.CV↗

arXiv2024

Ultrafast Electron Diffraction with MeV Electron Source from a Laser Wakefield Accelerator

MeV ultrafast electron diffraction (UED) is a widely used technology for ultrafast structural dynamic studies of matters in numerous areas. The development of laser wakefield accelerator (LWFA) envisions great potential of advanced all-optical electron source based on LWFA in UED applications. We experimentally demonstrated that an LWFA-based device with a miniaturized permanent magnet beamline can generate and manipulate electron beams suitable for UED. In the beam transmission, the LWFA electron beams with intrinsic short duration stretch due to energy spread and then are compressed by a following double bend achromat. The optimized double bend achromat can make the beamline isochronous such that the arrival time jitter induced by the shot-to-shot energy fluctuation can be eliminated, and allow the advantage of the natural laser-beam synchronization for LWFAs to emerge. With the energy filtering, the beam energy spread can be reduced to 3% (FWHM) while a sufficient amount of charge (11.9 fC) per bunch for diffraction is retained. Start-to-end simulations showed that the bunch length reaches ~30 fs (rms) with the same experimental configuration. Clear single-shot and multi-shot diffraction patterns of single-crystalline gold samples are obtained and the derived lattice constant agrees excellently with the real value. Our proof-of-principle experiments open the door to the detection of ultrafast structural dynamics using MeV LWFA beams, and pave the way for the UED applications with sub-10-fs temporal resolution.

physics.acc-ph↗

arXiv2024

Low-dose CT Denoising with Language-engaged Dual-space Alignment

While various deep learning methods were proposed for low-dose computed tomography (CT) denoising, they often suffer from over-smoothing, blurring, and lack of explainability. To alleviate these issues, we propose a plug-and-play Language-Engaged Dual-space Alignment loss (LEDA) to optimize low-dose CT denoising models. Our idea is to leverage large language models (LLMs) to align denoised CT and normal dose CT images in both the continuous perceptual space and discrete semantic space, which is the first LLM-based scheme for low-dose CT denoising. LEDA involves two steps: the first is to pretrain an LLM-guided CT autoencoder, which can encode a CT image into continuous high-level features and quantize them into a token space to produce semantic tokens derived from the LLM's vocabulary; and the second is to minimize the discrepancy between the denoised CT images and normal dose CT in terms of both encoded high-level features and quantized token embeddings derived by the LLM-guided CT autoencoder. Extensive experimental results on two public LDCT denoising datasets demonstrate that our LEDA can enhance existing denoising models in terms of quantitative metrics and qualitative evaluation, and also provide explainability through language-level image understanding. Source code is available at https://github.com/hao1635/LEDA.

eess.IV↗

arXiv2024

Exploiting Emotion-Semantic Correlations for Empathetic Response Generation

Empathetic response generation aims to generate empathetic responses by understanding the speaker's emotional feelings from the language of dialogue. Recent methods capture emotional words in the language of communicators and construct them as static vectors to perceive nuanced emotions. However, linguistic research has shown that emotional words in language are dynamic and have correlations with other grammar semantic roles, i.e., words with semantic meanings, in grammar. Previous methods overlook these two characteristics, which easily lead to misunderstandings of emotions and neglect of key semantics. To address this issue, we propose a dynamical Emotion-Semantic Correlation Model (ESCM) for empathetic dialogue generation tasks. ESCM constructs dynamic emotion-semantic vectors through the interaction of context and emotions. We introduce dependency trees to reflect the correlations between emotions and semantics. Based on dynamic emotion-semantic vectors and dependency trees, we propose a dynamic correlation graph convolutional network to guide the model in learning context meanings in dialogue and generating empathetic responses. Experimental results on the EMPATHETIC-DIALOGUES dataset show that ESCM understands semantics and emotions more accurately and expresses fluent and informative empathetic responses. Our analysis results also indicate that the correlations between emotions and semantics are frequently used in dialogues, which is of great significance for empathetic perception and expression.

cs.CL↗

arXiv2024

Training-free image style alignment for self-adapting domain shift on handheld ultrasound devices

Handheld ultrasound devices face usage limitations due to user inexperience and cannot benefit from supervised deep learning without extensive expert annotations. Moreover, the models trained on standard ultrasound device data are constrained by training data distribution and perform poorly when directly applied to handheld device data. In this study, we propose the Training-free Image Style Alignment (TISA) framework to align the style of handheld device data to those of standard devices. The proposed TISA can directly infer handheld device images without extra training and is suited for clinical applications. We show that TISA performs better and more stably in medical detection and segmentation tasks for handheld device data. We further validate TISA as the clinical model for automatic measurements of spinal curvature and carotid intima-media thickness. The automatic measurements agree well with manual measurements made by human experts and the measurement errors remain within clinically acceptable ranges. We demonstrate the potential for TISA to facilitate automatic diagnosis on handheld ultrasound devices and expedite their eventual widespread use.

eess.IV↗

arXiv2024

Variable white dwarfs in TMTS: Asteroseismological analysis of a ZZ Ceti star, TMTS J17184064+2524314

The Tsinghua University-Ma Huateng Telescope for Survey (TMTS) has been constantly monitoring the northern sky since 2020 in search of rapidly variable stars. To find variable white dwarfs (WDs), the TMTS catalog is cross-matched with the WD catalog of Gaia EDR3, resulting in over 3000 light curves of WD candidates. The WD TMTS J17184064+2524314 (hereafter J1718) is the second ZZ~Ceti star discovered among these common sources. Based on the light curves from TMTS, follow-up photometric observations, and TESS, 10 periods and 3 combination periods are detected. A rotation period of $25.12\pm0.18$ hr is derived, according to the identified rotational splitting. Our spectroscopic observation indicates that this WD belongs to DA type with $T_{\rm eff}=11,670\pm604$ K, log $g=8.16\pm0.36$, $M = 0.70\pm0.23$ M$_{\odot}$, and age=$0.51\pm0.34$ Gyr. Based on core-parameterized asteroseismological model grids ($\geqslant$ 14 million), we derive a best-fit solution of $T_{\rm eff}=11,640\pm20$ K, log $g=8.267\pm0.008$, and $M = 0.750\pm0.005$ M$_{\odot}$ for J1718, consistent with the spectral fitting results. For this WD, the corresponding carbon and oxygen abundances in the core are 0.43 and 0.57, respectively. The distance derived from the intrinsic luminosity given by asteroseismology is $64\pm15$ pc, in accord with the distance of $70.1\pm0.2$ pc from Gaia DR3 within the uncertainties.

astro-ph.SR↗

arXiv2024

A spectral data release for 104 Type II Supernovae from the Tsinghua Supernova Group

We present 206 unpublished optical spectra of 104 type II supernovae obtained by the Xinglong 2.16m telescope and Lijiang 2.4m telescope during the period from 2011 to 2018, spanning the phases from about 1 to 200 days after the SN explosion. The spectral line identifications, evolution of line velocities and pseudo equivalent widths, as well as correlations between some important spectral parameters are presented. Our sample displays a large range in expansion velocities. For instance, the Fe~{\sc ii} $5169$ velocities measured from spectra at $t\sim 50$ days after the explosion vary from ${\rm 2000\ km\ s^{-1}}$ to ${\rm 5500\ km\ s^{-1}}$, with an average value of ${\rm 3872 \pm 949\ km\ s^{-1}}$. Power-law functions can be used to fit the velocity evolution, with the power-law exponent quantifying the velocity decline rate. We found an anticorrelation existing between H$β$ velocity at mid-plateau phase and its velocity decay exponent, SNe II with higher velocities tending to have smaller velocity decay rate. Moreover, we noticed that the velocity decay rate inferred from the Balmer lines (i.e., H$α$ and H$β$) have moderate correlations with the ratio of absorption to emission for H$α$ (a/e). In our sample, two objects show possibly flash-ionized features at early phases. Besides, we noticed that multiple high-velocity components may exist on the blue side of hydrogen lines of SN 2013ab, possibly suggesting that these features arise from complex line forming region. All our spectra can be found in WISeREP and Zenodo.

astro-ph.HE↗

arXiv2024

LIT-Former: Linking In-plane and Through-plane Transformers for Simultaneous CT Image Denoising and Deblurring

This paper studies 3D low-dose computed tomography (CT) imaging. Although various deep learning methods were developed in this context, typically they focus on 2D images and perform denoising due to low-dose and deblurring for super-resolution separately. Up to date, little work was done for simultaneous in-plane denoising and through-plane deblurring, which is important to obtain high-quality 3D CT images with lower radiation and faster imaging speed. For this task, a straightforward method is to directly train an end-to-end 3D network. However, it demands much more training data and expensive computational costs. Here, we propose to link in-plane and through-plane transformers for simultaneous in-plane denoising and through-plane deblurring, termed as LIT-Former, which can efficiently synergize in-plane and through-plane sub-tasks for 3D CT imaging and enjoy the advantages of both convolution and transformer networks. LIT-Former has two novel designs: efficient multi-head self-attention modules (eMSM) and efficient convolutional feedforward networks (eCFN). First, eMSM integrates in-plane 2D self-attention and through-plane 1D self-attention to efficiently capture global interactions of 3D self-attention, the core unit of transformer networks. Second, eCFN integrates 2D convolution and 1D convolution to extract local information of 3D convolution in the same fashion. As a result, the proposed LIT-Former synergize these two subtasks, significantly reducing the computational complexity as compared to 3D counterparts and enabling rapid convergence. Extensive experimental results on simulated and clinical datasets demonstrate superior performance over state-of-the-art models. The source code is made available at https://github.com/hao1635/LIT-Former.

eess.IV↗

arXiv2023

IQAGPT: Image Quality Assessment with Vision-language and ChatGPT Models

Large language models (LLMs), such as ChatGPT, have demonstrated impressive capabilities in various tasks and attracted an increasing interest as a natural language interface across many domains. Recently, large vision-language models (VLMs) like BLIP-2 and GPT-4 have been intensively investigated, which learn rich vision-language correlation from image-text pairs. However, despite these developments, the application of LLMs and VLMs in image quality assessment (IQA), particularly in medical imaging, remains to be explored, which is valuable for objective performance evaluation and potential supplement or even replacement of radiologists' opinions. To this end, this paper introduces IQAGPT, an innovative image quality assessment system integrating an image quality captioning VLM with ChatGPT for generating quality scores and textual reports. First, we build a CT-IQA dataset for training and evaluation, comprising 1,000 CT slices with diverse quality levels professionally annotated. To better leverage the capabilities of LLMs, we convert annotated quality scores into semantically rich text descriptions using a prompt template. Second, we fine-tune the image quality captioning VLM on the CT-IQA dataset to generate quality descriptions. The captioning model fuses the image and text features through cross-modal attention. Third, based on the quality descriptions, users can talk with ChatGPT to rate image quality scores or produce a radiological quality report. Our preliminary results demonstrate the feasibility of assessing image quality with large models. Remarkably, our IQAGPT outperforms GPT-4 and CLIP-IQA, as well as the multi-task classification and regression models that solely rely on images.

cs.CV↗

arXiv2023

SN 2022vqz: A Peculiar Subluminous Type Ia Supernova with Prominent Early Excess Emission

We present extensive photometric and spectroscopic observations of the peculiar Type Ia supernova (SN Ia) 2022vqz. It shares many similarities with the SN 2002es-like SNe Ia, such as low luminosity ($M_{B,\rm max}=-18.11\pm0.16$ mag) and moderate post-peak decline rate ($Δm_{15,B}=1.33\pm0.11$ mag). The nickel mass synthesised in the explosion is estimated as $0.20\pm0.04~{\rm M}_\odot$ from the bolometric light curve, which is obviously lower than that of normal SNe Ia. SN 2022vqz is also characterised by slowly expanding ejecta, with Si II velocities persisting around 7000 km s$^{-1}$ since 16 days before peak brightness, unique among all known SNe Ia. While all of these properties imply a lower-energy thermonuclear explosion that should leave a considerable amount of unburnt materials, the absent signature of unburnt carbon in spectra of SN 2022vqz is puzzling. A prominent early peak is clearly detected in the ATLAS $c$- and $o$-band light curves and in the ZTF $gr$-band data within days after the explosion. Possible mechanisms for the early peak are discussed, including the sub-Chandrasekhar-mass double-detonation model and interaction of SN ejecta with circumstellar material. We find that both models face some difficulties in replicating all aspects of the observed data. As an alternative, we propose a hybrid C-O-Ne white dwarf as the progenitor of SN 2022vqz; it can simultaneously reconcile the tension between low ejecta velocity and the absence of carbon. We further discuss the diversity of SN 2002es-like objects and their origin in the context of different scenarios.

astro-ph.HE↗

arXiv2023

1100 days in the life of the supernova 2018ibb -- The best pair-instability supernova candidate, to date

Abridged - Stars with ZAMS masses between 140 and $260 M_\odot$ are thought to explode as pair-instability supernovae (PISNe). During their thermonuclear runaway, PISNe can produce up to several tens of solar masses of radioactive nickel, resulting in luminous transients similar to some superluminous supernovae (SLSNe). Yet, no unambiguous PISN has been discovered so far. SN2018ibb is a H-poor SLSN at $z=0.166$ that evolves extremely slowly compared to the hundreds of known SLSNe. Between mid 2018 and early 2022, we monitored its photometric and spectroscopic evolution from the UV to the NIR with 2-10m class telescopes. SN2018ibb radiated $>3\times10^{51} \rm erg$ during its evolution, and its bolometric light curve reached $>2\times10^{44} \rm erg\,s^{-1}$ at peak. The long-lasting rise of $>93$ rest-frame days implies a long diffusion time, which requires a very high total ejected mass. The PISN mechanism naturally provides both the energy source ($^{56}$Ni) and the long diffusion time. Theoretical models of PISNe make clear predictions for their photometric and spectroscopic properties. SN2018ibb complies with most tests on the light curves, nebular spectra and host galaxy, potentially all tests with the interpretation we propose. Both the light curve and the spectra require 25-44 $M_\odot$ of freshly nucleosynthesised $^{56}$Ni, pointing to the explosion of a metal-poor star with a He-core mass of 120-130 $M_\odot$ at the time of death. This interpretation is also supported by the tentative detection of [Co II]$λ$1.025$μ$m, which has never been observed in any other PISN candidate or SLSN before. Powering by a central engine, such as a magnetar or a black hole, can be excluded with high confidence. This makes SN2018ibb by far the best candidate for being a PISN, to date.

astro-ph.HE↗