arXiv subjects

Yuchen Guo

Publications and source records attributed to Yuchen Guo.

At least 55 records · Page 3Linked to original sources

arXiv2025

SparseFormer: Detecting Objects in HRW Shots via Sparse Vision Transformer

Recent years have seen an increase in the use of gigapixel-level image and video capture systems and benchmarks with high-resolution wide (HRW) shots. However, unlike close-up shots in the MS COCO dataset, the higher resolution and wider field of view raise unique challenges, such as extreme sparsity and huge scale changes, causing existing close-up detectors inaccuracy and inefficiency. In this paper, we present a novel model-agnostic sparse vision transformer, dubbed SparseFormer, to bridge the gap of object detection between close-up and HRW shots. The proposed SparseFormer selectively uses attentive tokens to scrutinize the sparsely distributed windows that may contain objects. In this way, it can jointly explore global and local attention by fusing coarse- and fine-grained features to handle huge scale changes. SparseFormer also benefits from a novel Cross-slice non-maximum suppression (C-NMS) algorithm to precisely localize objects from noisy windows and a simple yet effective multi-scale strategy to improve accuracy. Extensive experiments on two HRW benchmarks, PANDA and DOTA-v1.0, demonstrate that the proposed SparseFormer significantly improves detection accuracy (up to 5.8%) and speed (up to 3x) over the state-of-the-art approaches.

cs.CV↗

arXiv2025

The Cosmic Evolution Early Release Science Survey (CEERS)

We present the Cosmic Evolution Early Release Science (CEERS) Survey, a 77.2 hour Director's Discretionary Early Release Science Program. CEERS demonstrates, tests, and validates efficient extragalactic surveys using coordinated, overlapping parallel observations with the JWST instrument suite, including NIRCam and MIRI imaging, NIRSpec low (R~100) and medium (R~1000) resolution spectroscopy, and NIRCam slitless grism (R~1500) spectroscopy. CEERS targets the Hubble Space Telescope-observed region of the Extended Groth Strip (EGS) field, supported by a rich set of multiwavelength data. CEERS facilitated immediate community science in both of the extragalactic core JWST science drivers ``First Light" and ``Galaxy Assembly," including: 1) The discovery and characterization of large samples of galaxies at z >~ 10 from ~90 arcmin^2 of NIRCam imaging, constraining their abundance and physical nature; 2) Deep spectra of >1000 galaxies, including dozens of galaxies at 6 3; and 4) Characterizing galaxy mid-IR emission with MIRI to study dust-obscured star-formation and supermassive black hole growth at z~1-3. As a legacy product for the community, the CEERS team has provided several data releases, accompanied by detailed notes on the data reduction procedures and notebooks to aid in reproducibility. In addition to an overview of the survey and quality of the data, we provide science highlights from the first two years with CEERS data.

astro-ph.GA↗

arXiv2024

Exploring Barred Galaxies in the Young Universe at $z\sim$2 Using $\textit{JWST}$ CEERS Data

Studying barred galaxies at early epochs can shed light on the early evolution of stellar bars, their impact on secular evolution and the star formation activity of young galaxies, and the origins of present-day barred galaxies like the Milky Way. We analyze data from the James Webb Space Telescope (JWST) Cosmic Evolution Early Release Science (CEERS) Survey to explore the impact of rest-frame wavelength and spatial resolution on detecting and characterizing some of the youngest barred galaxies known to date. We apply both visual classification and ellipse-fitting to JWST F115W, F200W, and F444W images of the barred galaxy CEERS-30155 at $z\sim$2.136, an epoch when the universe was only $\sim$22$\%$ of its current age. We find that the stellar bar in CEERS-30155 is not visible in the F115W image, which traces rest-frame ultraviolet (UV) light at $z\sim$2, a rest-frame wavelength highly obscured by dust. The stellar bar is visible in the F200W image, but is most prominent in the F444W image, likely due to the F444W image tracing rest-frame near-infrared (NIR) light at $z\sim$2. Rest-frame NIR light is not obscured by dust and traces low-mass, long-lived stars that dominate the stellar mass in galaxies. However, ellipse fits of the F444W image only robustly detect stellar bars whose semimajor axis are at least one PSF ($\sim$ 0.16" or $\sim$ 1.4 kpc at $z\sim$2). At $z\sim$2, stellar bars smaller than 1.5 kpc will be more robustly detected in the sharper F200W image (PSF $\sim$ 0.08" or $\sim$0.7 kpc at $z\sim$2), provided that the rest-frame optical light it traces is not overly impacted by dust and can still unveil the bar structure. Using a combination of both JWST F200W and F444W images can improve the detection of barred galaxies at $z\sim$2 to 4. At even higher redshifts (z > 4), the Giant Magellan Telescope will be a cornerstone facility to explore young barred galaxies.

astro-ph.GA↗

arXiv2024

Locally purified density operators for noisy quantum circuits

Simulating open quantum systems is essential for exploring novel quantum phenomena and evaluating noisy quantum circuits. In this Letter, we address the problem of whether mixed states generated from noisy quantum circuits can be efficiently represented by locally purified density operators (LPDOs). We map an LPDO of $N$ qubits to a pure state of size $2\times N$ defined on a ladder and introduce a unified method for managing virtual and Kraus bonds. We numerically simulate noisy random quantum circuits with depths up to $d=40$ using fidelity and entanglement entropy as accuracy measures. LPDO representation proves to be effective in describing mixed states in both quantum and classical regions but encounters significant challenges at the quantum-classical critical point, limiting its applicability to the quantum region exclusively. In contrast, the matrix product operator (MPO) successfully characterizes the entanglement trend throughout the simulation, while truncation in MPOs breaks the positivity condition required for a physical density matrix. This work advances our understanding of efficient mixed-state representation in open quantum systems and provides insights into the entanglement structure of noisy quantum circuits.

quant-ph↗

arXiv2024

Corner2Net: Detecting Objects as Cascade Corners

The corner-based detection paradigm enjoys the potential to produce high-quality boxes. But the development is constrained by three factors: 1) Hard to match corners. Heuristic corner matching algorithms can lead to incorrect boxes, especially when similar-looking objects co-occur. 2) Poor instance context. Two separate corners preserve few instance semantics, so it is difficult to guarantee getting both two class-specific corners on the same heatmap channel. 3) Unfriendly backbone. The training cost of the hourglass network is high. Accordingly, we build a novel corner-based framework, named Corner2Net. To achieve the corner-matching-free manner, we devise the cascade corner pipeline which progressively predicts the associated corner pair in two steps instead of synchronously searching two independent corners via parallel heads. Corner2Net decouples corner localization and object classification. Both two corners are class-agnostic and the instance-specific bottom-right corner further simplifies its search space. Meanwhile, RoI features with rich semantics are extracted for classification. Popular backbones (e.g., ResNeXt) can be easily connected to Corner2Net. Experimental results on COCO show Corner2Net surpasses all existing corner-based detectors by a large margin in accuracy and speed.

cs.CV↗

arXiv2024

Enabling Explainable Recommendation in E-commerce with LLM-powered Product Knowledge Graph

How to leverage large language model's superior capability in e-commerce recommendation has been a hot topic. In this paper, we propose LLM-PKG, an efficient approach that distills the knowledge of LLMs into product knowledge graph (PKG) and then applies PKG to provide explainable recommendations. Specifically, we first build PKG by feeding curated prompts to LLM, and then map LLM response to real enterprise products. To mitigate the risks associated with LLM hallucination, we employ rigorous evaluation and pruning methods to ensure the reliability and availability of the KG. Through an A/B test conducted on an e-commerce website, we demonstrate the effectiveness of LLM-PKG in driving user engagements and transactions significantly.

cs.IR↗

arXiv2024

Quantum State Tomography with Locally Purified Density Operators and Local Measurements

Understanding quantum systems is of significant importance for assessing the performance of quantum hardware and software, as well as exploring quantum control and quantum sensing. An efficient representation of quantum states enables realizing quantum state tomography with minimal measurements. In this study, we propose an alternative approach to state tomography that uses tensor network representations of mixed states through locally purified density operators and employs a classical data postprocessing algorithm requiring only local measurements. Through numerical simulations of one-dimensional pure and mixed states and two-dimensional pure states up to size $8\times 8$, we demonstrate the efficiency, accuracy, and robustness of our proposed methods. Experiments on the IBM and Quafu Quantum platforms complement these numerical simulations. Our study opens avenues in quantum state tomography for two-dimensional systems using tensor network formalism.

quant-ph↗

arXiv2024

DynamicTrack: Advancing Gigapixel Tracking in Crowded Scenes

Tracking in gigapixel scenarios holds numerous potential applications in video surveillance and pedestrian analysis. Existing algorithms attempt to perform tracking in crowded scenes by utilizing multiple cameras or group relationships. However, their performance significantly degrades when confronted with complex interaction and occlusion inherent in gigapixel images. In this paper, we introduce DynamicTrack, a dynamic tracking framework designed to address gigapixel tracking challenges in crowded scenes. In particular, we propose a dynamic detector that utilizes contrastive learning to jointly detect the head and body of pedestrians. Building upon this, we design a dynamic association algorithm that effectively utilizes head and body information for matching purposes. Extensive experiments show that our tracker achieves state-of-the-art performance on widely used tracking benchmarks specifically designed for gigapixel crowded scenes.

cs.CV↗

arXiv2024

SaccadeDet: A Novel Dual-Stage Architecture for Rapid and Accurate Detection in Gigapixel Images

The advancement of deep learning in object detection has predominantly focused on megapixel images, leaving a critical gap in the efficient processing of gigapixel images. These super high-resolution images present unique challenges due to their immense size and computational demands. To address this, we introduce 'SaccadeDet', an innovative architecture for gigapixel-level object detection, inspired by the human eye saccadic movement. The cornerstone of SaccadeDet is its ability to strategically select and process image regions, dramatically reducing computational load. This is achieved through a two-stage process: the 'saccade' stage, which identifies regions of probable interest, and the 'gaze' stage, which refines detection in these targeted areas. Our approach, evaluated on the PANDA dataset, not only achieves an 8x speed increase over the state-of-the-art methods but also demonstrates significant potential in gigapixel-level pathology analysis through its application to Whole Slide Imaging.

cs.CV↗

arXiv2024

Deep Learning-Based Quasi-Conformal Surface Registration for Partial 3D Faces Applied to Facial Recognition

3D face registration is an important process in which a 3D face model is aligned and mapped to a template face. However, the task of 3D face registration becomes particularly challenging when dealing with partial face data, where only limited facial information is available. To address this challenge, this paper presents a novel deep learning-based approach that combines quasi-conformal geometry with deep neural networks for partial face registration. The proposed framework begins with a Landmark Detection Network that utilizes curvature information to detect the presence of facial features and estimate their corresponding coordinates. These facial landmark features serve as essential guidance for the registration process. To establish a dense correspondence between the partial face and the template surface, a registration network based on quasiconformal theories is employed. The registration network establishes a bijective quasiconformal surface mapping aligning corresponding partial faces based on detected landmarks and curvature values. It consists of the Coefficients Prediction Network, which outputs the optimal Beltrami coefficient representing the surface mapping. The Beltrami coefficient quantifies the local geometric distortion of the mapping. By controlling the magnitude of the Beltrami coefficient through a suitable activation function, the bijectivity and geometric distortion of the mapping can be controlled. The Beltrami coefficient is then fed into the Beltrami solver network to reconstruct the corresponding mapping. The surface registration enables the acquisition of corresponding regions and the establishment of point-wise correspondence between different partial faces, facilitating precise shape comparison through the evaluation of point-wise geometric differences at these corresponding regions. Experimental results demonstrate the effectiveness of the proposed method.

cs.CV↗

arXiv2024

Improving classifier-based effort-aware software defect prediction by reducing ranking errors

Context: Software defect prediction utilizes historical data to direct software quality assurance resources to potentially problematic components. Effort-aware (EA) defect prediction prioritizes more bug-like components by taking cost-effectiveness into account. In other words, it is a ranking problem, however, existing ranking strategies based on classification, give limited consideration to ranking errors. Objective: Improve the performance of classifier-based EA ranking methods by focusing on ranking errors. Method: We propose a ranking score calculation strategy called EA-Z which sets a lower bound to avoid near-zero ranking errors. We investigate four primary EA ranking strategies with 16 classification learners, and conduct the experiments for EA-Z and the other four existing strategies. Results: Experimental results from 72 data sets show EA-Z is the best ranking score calculation strategy in terms of Recall@20% and Popt when considering all 16 learners. For particular learners, imbalanced ensemble learner UBag-svm and UBst-rf achieve top performance with EA-Z. Conclusion: Our study indicates the effectiveness of reducing ranking errors for classifier-based effort-aware defect prediction. We recommend using EA-Z with imbalanced ensemble learning.

cs.SE↗

arXiv2024

Debiased Novel Category Discovering and Localization

In recent years, object detection in deep learning has experienced rapid development. However, most existing object detection models perform well only on closed-set datasets, ignoring a large number of potential objects whose categories are not defined in the training set. These objects are often identified as background or incorrectly classified as pre-defined categories by the detectors. In this paper, we focus on the challenging problem of Novel Class Discovery and Localization (NCDL), aiming to train detectors that can detect the categories present in the training data, while also actively discover, localize, and cluster new categories. We analyze existing NCDL methods and identify the core issue: object detectors tend to be biased towards seen objects, and this leads to the neglect of unseen targets. To address this issue, we first propose an Debiased Region Mining (DRM) approach that combines class-agnostic Region Proposal Network (RPN) and class-aware RPN in a complementary manner. Additionally, we suggest to improve the representation network through semi-supervised contrastive learning by leveraging unlabeled data. Finally, we adopt a simple and efficient mini-batch K-means clustering method for novel class discovery. We conduct extensive experiments on the NCDL benchmark, and the results demonstrate that the proposed DRM approach significantly outperforms previous methods, establishing a new state-of-the-art.

cs.CV↗

arXiv2024

CollabCoder: A Lower-barrier, Rigorous Workflow for Inductive Collaborative Qualitative Analysis with Large Language Models

Collaborative Qualitative Analysis (CQA) can enhance qualitative analysis rigor and depth by incorporating varied viewpoints. Nevertheless, ensuring a rigorous CQA procedure itself can be both demanding and costly. To lower this bar, we take a theoretical perspective to design the CollabCoder workflow, that integrates Large Language Models (LLMs) into key inductive CQA stages: independent open coding, iterative discussions, and final codebook creation. In the open coding phase, CollabCoder offers AI-generated code suggestions and records decision-making data. During discussions, it promotes mutual understanding by sharing this data within the coding team and using quantitative metrics to identify coding (dis)agreements, aiding in consensus-building. In the code grouping stage, CollabCoder provides primary code group suggestions, lightening the cognitive load of finalizing the codebook. A 16-user evaluation confirmed the effectiveness of CollabCoder, demonstrating its advantages over existing software and providing empirical insights into the role of LLMs in the CQA practice.

cs.HC↗

arXiv2024

Enhancing Robustness of LLM-Synthetic Text Detectors for Academic Writing: A Comprehensive Analysis

The emergence of large language models (LLMs), such as Generative Pre-trained Transformer 4 (GPT-4) used by ChatGPT, has profoundly impacted the academic and broader community. While these models offer numerous advantages in terms of revolutionizing work and study methods, they have also garnered significant attention due to their potential negative consequences. One example is generating academic reports or papers with little to no human contribution. Consequently, researchers have focused on developing detectors to address the misuse of LLMs. However, most existing methods prioritize achieving higher accuracy on restricted datasets, neglecting the crucial aspect of generalizability. This limitation hinders their practical application in real-life scenarios where reliability is paramount. In this paper, we present a comprehensive analysis of the impact of prompts on the text generated by LLMs and highlight the potential lack of robustness in one of the current state-of-the-art GPT detectors. To mitigate these issues concerning the misuse of LLMs in academic writing, we propose a reference-based Siamese detector named Synthetic-Siamese which takes a pair of texts, one as the inquiry and the other as the reference. Our method effectively addresses the lack of robustness of previous detectors (OpenAI detector and DetectGPT) and significantly improves the baseline performances in realistic academic writing scenarios by approximately 67% to 95%.

cs.CL↗

arXiv2024

Galaxies Going Bananas: Inferring the 3D Geometry of High-Redshift Galaxies with JWST-CEERS

The 3D geometry of high-redshift galaxies remains poorly understood. We build a differentiable Bayesian model and use Hamiltonian Monte Carlo to efficiently and robustly infer the 3D shapes of star-forming galaxies in JWST-CEERS observations with $\log M_*/M_{\odot}=9.0-10.5$ at $z=0.5-8.0$. We reproduce previous results from HST-CANDELS in a fraction of the computing time and constrain the mean ellipticity, triaxiality, size and covariances with samples as small as $\sim50$ galaxies. We find high 3D ellipticities for all mass-redshift bins suggesting oblate (disky) or prolate (elongated) geometries. We break that degeneracy by constraining the mean triaxiality to be $\sim1$ for $\log M_*/M_{\odot}=9.0-9.5$ dwarfs at $z>1$ (favoring the prolate scenario), with significantly lower triaxialities for higher masses and lower redshifts indicating the emergence of disks. The prolate population traces out a ``banana'' in the projected $b/a-\log a$ diagram with an excess of low $b/a$, large $\log a$ galaxies. The dwarf prolate fraction rises from $\sim25\%$ at $z=0.5-1.0$ to $\sim50-80\%$ at $z=3-8$. If these are disks, they cannot be axisymmetric but instead must be unusually oval (triaxial) unlike local circular disks. We simultaneously constrain the 3D size-mass relation and its dependence on 3D geometry. High-probability prolate and oblate candidates show remarkably similar Sérsic indices ($n\sim1$), non-parametric morphological properties and specific star formation rates. Both tend to be visually classified as disks or irregular but edge-on oblate candidates show more dust attenuation. We discuss selection effects, follow-up prospects and theoretical implications.

astro-ph.GA↗

arXiv2023

The Impact of Far-Infrared/Sub-Millimeter Data on the Star Formation Rates of Massive Dusty Galaxies at Cosmic Noon

We explore how the star formation rate (SFR), stellar mass, and other properties of massive dusty galaxies at cosmic noon are impacted when far-infrared (FIR)/sub-millimeter data are added to datasets containing only ultraviolet (UV) to near-infrared (NIR) data. For a sample of 92 massive (stellar mass $> 4{\times}10^{10}$ M$_{\odot}$) dusty galaxies at $z\,{\sim}\,1.5$ to 3.0 (corresponding to ${\sim}25$% of cosmic history), we fit the spectral energy distributions (SEDs) based on DECam UV-to-optical data, VICS82, NEWFIRM, and Spitzer-IRAC NIR data, and Herschel-SPIRE FIR/sub-millimeter data using the Bayesian Analysis of Galaxies for Physical Inference and Parameter Estimation (BAGPIPES) SED-fitting code. We assume a delayed tau star formation history with a log$_{10}$ prior on tau and derive the posterior distributions of stellar mass, SFR, extinction, and specific SFR. We find that adding FIR/sub-millimeter data leads to SFR estimates that can be both significantly higher or lower (typically by up to a factor of 10) than estimates based on UV-to-NIR data alone, depending on the type of galaxies involved. We find that the changes in SFR scale with changes in extinction. These results highlight the importance of including FIR/sub-millimeter data in order to accurately derive the SFRs of massive dusty galaxies at $z\,{\sim}\,2$.

astro-ph.GA↗

arXiv2023

Human-Machine Cooperative Multimodal Learning Method for Cross-subject Olfactory Preference Recognition

Odor sensory evaluation has a broad application in food, clothing, cosmetics, and other fields. Traditional artificial sensory evaluation has poor repeatability, and the machine olfaction represented by the electronic nose (E-nose) is difficult to reflect human feelings. Olfactory electroencephalogram (EEG) contains odor and individual features associated with human olfactory preference, which has unique advantages in odor sensory evaluation. However, the difficulty of cross-subject olfactory EEG recognition greatly limits its application. It is worth noting that E-nose and olfactory EEG are more advantageous in representing odor information and individual emotions, respectively. In this paper, an E-nose and olfactory EEG multimodal learning method is proposed for cross-subject olfactory preference recognition. Firstly, the olfactory EEG and E-nose multimodal data acquisition and preprocessing paradigms are established. Secondly, a complementary multimodal data mining strategy is proposed to effectively mine the common features of multimodal data representing odor information and the individual features in olfactory EEG representing individual emotional information. Finally, the cross-subject olfactory preference recognition is achieved in 24 subjects by fusing the extracted common and individual features, and the recognition effect is superior to the state-of-the-art recognition methods. Furthermore, the advantages of the proposed method in cross-subject olfactory preference recognition indicate its potential for practical odor evaluation applications.

cs.AI↗

arXiv2023

A Milky Way-like barred spiral galaxy at a redshift of 3

The majority of massive disk galaxies in the local Universe show a stellar barred structure in their central regions, including our Milky Way. Bars are supposed to develop in dynamically cold stellar disks at low redshift, as the strong gas turbulence typical of disk galaxies at high redshift suppresses or delays bar formation. Moreover, simulations predict bars to be almost absent beyond $z = 1.5$ in the progenitors of Milky Way-like galaxies. Here we report observations of ceers-2112, a barred spiral galaxy at redshift $z_{\rm phot} \sim 3$, which was already mature when the Universe was only 2 Gyr old. The stellar mass ($M_{\star} = 3.9 \times 10^9 M_{\odot}$) and barred morphology mean that ceers-2112 can be considered a progenitor of the Milky Way, in terms of both structure and mass-assembly history in the first 2 Gyr of the Universe, and was the closest in mass in the first 4 Gyr. We infer that baryons in galaxies could have already dominated over dark matter at $z \sim 3$, that high-redshift bars could form in approximately 400 Myr and that dynamically cold stellar disks could have been in place by redshift $z = 4-5$ (more than 12 Gyrs ago).

astro-ph.GA↗