arXiv subjects

Yuchen Guo

Publications and source records attributed to Yuchen Guo.

At least 91 records · Page 5Linked to original sources

arXiv2022

CEERS Key Paper III: The Resolved Host Properties of AGN at 3 < z < 5 with JWST

We report on the host properties of five X-ray luminous Active Galactic Nuclei (AGN) identified at $3 < z < 5$ in the first epoch of imaging from the Cosmic Evolution Early Release Science Survey (CEERS). Each galaxy has been imaged with the \textit{James Webb Space Telescope} (\jwst) Near-Infrared Camera (NIRCam), which provides spatially resolved, rest-frame optical morphologies at these redshifts. We also derive stellar masses and star formation rates for each host galaxy by fitting its spectral energy distribution using a combination of galaxy and AGN templates. The AGN hosts have an average stellar mass of ${\rm log}(M_{*}/{\rm M_{\odot}} )= 11.0$, making them among the most massive galaxies detected at this redshift range in the current CEERS pointings, even after accounting for nuclear light from the AGN. We find that three of the AGN hosts have spheroidal morphologies, one is a bulge-dominated disk and one host is dominated by point-like emission. None are found to show strong morphological disturbances that might indicate a recent interaction or merger event. Notably, all four of the resolved hosts have rest-frame optical colors consistent with a quenched or post-starburst stellar population. The presence of AGN in passively evolving galaxies at $z>3$ is significant because a rapid feedback mechanism is required in most semi-analytic models and cosmological simulations to explain the growing population of massive quiescent galaxies observed at these redshifts. Our findings are in general agreement with this picture and show that AGN can continue to inject energy into these systems after their star formation is curtailed, possibly helping to maintain their quiescent state.

astro-ph.GA↗

arXiv2022

Automatic Landmark Detection and Registration of Brain Cortical Surfaces via Quasi-Conformal Geometry and Convolutional Neural Networks

In medical imaging, surface registration is extensively used for performing systematic comparisons between anatomical structures, with a prime example being the highly convoluted brain cortical surfaces. To obtain a meaningful registration, a common approach is to identify prominent features on the surfaces and establish a low-distortion mapping between them with the feature correspondence encoded as landmark constraints. Prior registration works have primarily focused on using manually labeled landmarks and solving highly nonlinear optimization problems, which are time-consuming and hence hinder practical applications. In this work, we propose a novel framework for the automatic landmark detection and registration of brain cortical surfaces using quasi-conformal geometry and convolutional neural networks. We first develop a landmark detection network (LD-Net) that allows for the automatic extraction of landmark curves given two prescribed starting and ending points based on the surface geometry. We then utilize the detected landmarks and quasi-conformal theory for achieving the surface registration. Specifically, we develop a coefficient prediction network (CP-Net) for predicting the Beltrami coefficients associated with the desired landmark-based registration and a mapping network called the disk Beltrami solver network (DBS-Net) for generating quasi-conformal mappings from the predicted Beltrami coefficients, with the bijectivity guaranteed by quasi-conformal theory. Experimental results are presented to demonstrate the effectiveness of our proposed framework. Altogether, our work paves a new way for surface-based morphometry and medical shape analysis.

cs.CV↗

arXiv2022

JDRec: Practical Actor-Critic Framework for Online Combinatorial Recommender System

A combinatorial recommender (CR) system feeds a list of items to a user at a time in the result page, in which the user behavior is affected by both contextual information and items. The CR is formulated as a combinatorial optimization problem with the objective of maximizing the recommendation reward of the whole list. Despite its importance, it is still a challenge to build a practical CR system, due to the efficiency, dynamics, personalization requirement in online environment. In particular, we tear the problem into two sub-problems, list generation and list evaluation. Novel and practical model architectures are designed for these sub-problems aiming at jointly optimizing effectiveness and efficiency. In order to adapt to online case, a bootstrap algorithm forming an actor-critic reinforcement framework is given to explore better recommendation mode in long-term user interaction. Offline and online experiment results demonstrate the efficacy of proposed JDRec framework. JDRec has been applied in online JD recommendation, improving click through rate by 2.6% and synthetical value for the platform by 5.03%. We will publish the large-scale dataset used in this study to contribute to the research community.

cs.IR↗

arXiv2022

A High-Accuracy Unsupervised Person Re-identification Method Using Auxiliary Information Mined from Datasets

Supervised person re-identification methods rely heavily on high-quality cross-camera training label. This significantly hinders the deployment of re-ID models in real-world applications. The unsupervised person re-ID methods can reduce the cost of data annotation, but their performance is still far lower than the supervised ones. In this paper, we make full use of the auxiliary information mined from the datasets for multi-modal feature learning, including camera information, temporal information and spatial information. By analyzing the style bias of cameras, the characteristics of pedestrians' motion trajectories and the positions of camera network, this paper designs three modules: Time-Overlapping Constraint (TOC), Spatio-Temporal Similarity (STS) and Same-Camera Penalty (SCP) to exploit the auxiliary information. Auxiliary information can improve the model performance and inference accuracy by constructing association constraints or fusing with visual features. In addition, this paper proposes three effective training tricks, including Restricted Label Smoothing Cross Entropy Loss (RLSCE), Weight Adaptive Triplet Loss (WATL) and Dynamic Training Iterations (DTI). The tricks achieve mAP of 72.4% and 81.1% on MARS and DukeMTMC-VideoReID, respectively. Combined with auxiliary information exploiting modules, our methods achieve mAP of 89.9% on DukeMTMC, where TOC, STS and SCP all contributed considerable performance improvements. The method proposed by this paper outperforms most existing unsupervised re-ID methods and narrows the gap between unsupervised and supervised re-ID methods. Our code is at https://github.com/tenghehan/AuxUSLReID.

cs.CV↗

arXiv2022

The Active Galactic Nuclei in the Hobby-Eberly Telescope Dark Energy Experiment Survey (HETDEX) I. Sample selection

We present the first Active Galactic Nuclei (AGN) catalog in the Hobby-Eberly Telescope Dark Energy Experiment Survey (HETDEX) observed between January 2017 and June 2020. HETDEX is an ongoing spectroscopic survey with no pre-selection based on magnitudes, colors or morphologies, enabling us to select AGN based on their spectral features. Both luminous quasars and low-luminosity Seyferts are found in our catalog. AGN candidates are selected with at least two significant AGN emission lines, such as the LyA and CIV line pair, or with single broad emission lines (FWHM > 1000 km/s). Each source is further confirmed by visual inspections. This catalog contains 5,322 AGN, covering an effective sky coverage of 30.61 deg^2. A total of 3,733 of these AGN have secure redshifts, and we provide redshift estimates for the remaining 1,589 single broad-line AGN with no cross matched spectral redshifts from SDSS DR14Q. The redshift range of the AGN catalog is 0.25 < z < 4.32, with a median of z = 2.1. The bolometric luminosity range is 10^9-10^14 Lsun with a median of 10^12 Lsun. The median r-band magnitude of the AGN is 21.6 mag, with 34% of the AGN have r > 22.5, and 2.6% reaching the detection limit at r ~ 26 mag of the deepest imaging surveys we searched. We also provide a composite spectrum of the AGN sample covering 700 AA - 4400 AA.

astro-ph.GA↗

arXiv2022

MP2: A Momentum Contrast Approach for Recommendation with Pointwise and Pairwise Learning

Binary pointwise labels (aka implicit feedback) are heavily leveraged by deep learning based recommendation algorithms nowadays. In this paper we discuss the limited expressiveness of these labels may fail to accommodate varying degrees of user preference, and thus lead to conflicts during model training, which we call annotation bias. To solve this issue, we find the soft-labeling property of pairwise labels could be utilized to alleviate the bias of pointwise labels. To this end, we propose a momentum contrast framework (MP2) that combines pointwise and pairwise learning for recommendation. MP2 has a three-tower network structure: one user network and two item networks. The two item networks are used for computing pointwise and pairwise loss respectively. To alleviate the influence of the annotation bias, we perform a momentum update to ensure a consistent item representation. Extensive experiments on real-world datasets demonstrate the superiority of our method against state-of-the-art recommendation algorithms.

cs.IR↗

arXiv2022

A Free Lunch to Person Re-identification: Learning from Automatically Generated Noisy Tracklets

A series of unsupervised video-based re-identification (re-ID) methods have been proposed to solve the problem of high labor cost required to annotate re-ID datasets. But their performance is still far lower than the supervised counterparts. In the mean time, clean datasets without noise are used in these methods, which is not realistic. In this paper, we propose to tackle this problem by learning re-ID models from automatically generated person tracklets by multiple objects tracking (MOT) algorithm. To this end, we design a tracklet-based multi-level clustering (TMC) framework to effectively learn the re-ID model from the noisy person tracklets. First, intra-tracklet isolation to reduce ID switch noise within tracklets; second, alternates between using inter-tracklet association to eliminate ID fragmentation noise and network training using the pseudo label. Extensive experiments on MARS with various manually generated noises show the effectiveness of the proposed framework. Specifically, the proposed framework achieved mAP 53.4% and rank-1 63.7% on the simulated tracklets with strongest noise, even outperforming the best existing method on clean tracklets. Based on the results, we believe that building re-ID models from automatically generated noisy tracklets is a reasonable approach and will also be an important way to make re-ID models feasible in real-world applications.

cs.CV↗

arXiv2021

TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification

Nowadays, real data in person re-identification (ReID) task is facing privacy issues, e.g., the banned dataset DukeMTMC-ReID. Thus it becomes much harder to collect real data for ReID task. Meanwhile, the labor cost of labeling ReID data is still very high and further hinders the development of the ReID research. Therefore, many methods turn to generate synthetic images for ReID algorithms as alternatives instead of real images. However, there is an inevitable domain gap between synthetic and real images. In previous methods, the generation process is based on virtual scenes, and their synthetic training data can not be changed according to different target real scenes automatically. To handle this problem, we propose a novel Target-Aware Generation pipeline to produce synthetic person images, called TAGPerson. Specifically, it involves a parameterized rendering method, where the parameters are controllable and can be adjusted according to target scenes. In TAGPerson, we extract information from target scenes and use them to control our parameterized rendering process to generate target-aware synthetic images, which would hold a smaller gap to the real images in the target domain. In our experiments, our target-aware synthetic images can achieve a much higher performance than the generalized synthetic images on MSMT17, i.e. 47.5% vs. 40.9% for rank-1 accuracy. We will release this toolkit\footnote{\noindent Code is available at \href{https://github.com/tagperson/tagperson-blender}{https://github.com/tagperson/tagperson-blender}} for the ReID community to generate synthetic images at any desired taste.

cs.CV↗

arXiv2021

AGN and Star Formation at Cosmic Noon: Comparison of Data to Theoretical Models

In theoretical models of galaxy evolution, AGN and star formation (SF) activity are closely linked and AGN feedback is routinely invoked to regulate galaxy growth. In order to constrain such models, we compare the hydrodynamical simulations IllustrisTNG and SIMBA, and the semi-analytical model SAG to the empirical results on AGN and SF at cosmic noon ($0.75 < z < 2.25$) reported in Florez et al. (2020). The empirical results are based on a large mass-complete sample drawn from 93,307 galaxies with and without high X-ray luminosity AGN ($L_X \gtrsim 10^{44}$ erg s$^{-1}$), selected from a 11.8 deg$^2$ area ($\sim 0.18$ Gpc$^3$ comoving volume at $z=0.75-2.25$). The main results of our comparisons are: (i) SAG and IllustrisTNG both qualitatively reproduce the empirical result that galaxies with high X-ray luminosity AGN have higher mean SFR, at a given stellar mass, than galaxies without such AGN. SAG, however, strongly over-produces the number density of high X-ray luminosity AGN by a factor of 10 to 100, while IllustrisTNG shows a lack of high X-ray luminosity AGN at high stellar mass ($M* > 10^{11} \ M_{\odot}$) at $z \sim 2$. (ii) In SIMBA, the mean SFR of galaxies with high X-ray luminosity AGN is lower than the SFR of galaxies without such AGN. Contrary to the data, many high X-ray luminosity AGN in SIMBA have quenched SF, suggesting that AGN feedback, or other feedback modes in galaxies with such AGN, might be too efficient in SIMBA.

astro-ph.GA↗

arXiv2021

LODE: Deep Local Deblurring and A New Benchmark

While recent deep deblurring algorithms have achieved remarkable progress, most existing methods focus on the global deblurring problem, where the image blur mostly arises from severe camera shake. We argue that the local blur, which is mostly derived from moving objects with a relatively static background, is prevalent but remains under-explored. In this paper, we first lay the data foundation for local deblurring by constructing, for the first time, a LOcal-DEblur (LODE) dataset consisting of 3,700 real-world captured locally blurred images and their corresponding ground-truth. Then, we propose a novel framework, termed BLur-Aware DEblurring network (BladeNet), which contains three components: the Local Blur Synthesis module generates locally blurred training pairs, the Local Blur Perception module automatically captures the locally blurred region and the Blur-guided Spatial Attention module guides the deblurring network with spatial attention. This framework is flexible such that it can be combined with many existing SotA algorithms. We carry out extensive experiments on REDS and LODE datasets showing that BladeNet improves PSNR by 2.5dB over SotAs for local deblurring while keeping comparable performance for global deblurring. We will publish the dataset and codes.

cs.CV↗

arXiv2021

ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting

We propose ResRep, a novel method for lossless channel pruning (a.k.a. filter pruning), which slims down a CNN by reducing the width (number of output channels) of convolutional layers. Inspired by the neurobiology research about the independence of remembering and forgetting, we propose to re-parameterize a CNN into the remembering parts and forgetting parts, where the former learn to maintain the performance and the latter learn to prune. Via training with regular SGD on the former but a novel update rule with penalty gradients on the latter, we realize structured sparsity. Then we equivalently merge the remembering and forgetting parts into the original architecture with narrower layers. In this sense, ResRep can be viewed as a successful application of Structural Re-parameterization. Such a methodology distinguishes ResRep from the traditional learning-based pruning paradigm that applies a penalty on parameters to produce sparsity, which may suppress the parameters essential for the remembering. ResRep slims down a standard ResNet-50 with 76.15% accuracy on ImageNet to a narrower one with only 45% FLOPs and no accuracy drop, which is the first to achieve lossless pruning with such a high compression ratio. The code and models are at https://github.com/DingXiaoH/ResRep.

cs.LG↗

arXiv2021

Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN

The existence of redundancy in Convolutional Neural Networks (CNNs) enables us to remove some filters/channels with acceptable performance drops. However, the training objective of CNNs usually tends to minimize an accuracy-related loss function without any attention paid to the redundancy, making the redundancy distribute randomly on all the filters, such that removing any of them may trigger information loss and accuracy drop, necessitating a following finetuning step for recovery. In this paper, we propose to manipulate the redundancy during training to facilitate network pruning. To this end, we propose a novel Centripetal SGD (C-SGD) to make some filters identical, resulting in ideal redundancy patterns, as such filters become purely redundant due to their duplicates; hence removing them does not harm the network. As shown on CIFAR and ImageNet, C-SGD delivers better performance because the redundancy is better organized, compared to the existing methods. The efficiency also characterizes C-SGD because it is as fast as regular SGD, requires no finetuning, and can be conducted simultaneously on all the layers even in very deep CNNs. Besides, C-SGD can improve the accuracy of CNNs by first training a model with the same architecture but wider layers then squeezing it into the original width.

cs.CV↗

arXiv2021

Zero-shot Node Classification with Decomposed Graph Prototype Network

Node classification is a central task in graph data analysis. Scarce or even no labeled data of emerging classes is a big challenge for existing methods. A natural question arises: can we classify the nodes from those classes that have never been seen? In this paper, we study this zero-shot node classification (ZNC) problem which has a two-stage nature: (1) acquiring high-quality class semantic descriptions (CSDs) for knowledge transfer, and (2) designing a well generalized graph-based learning model. For the first stage, we give a novel quantitative CSDs evaluation strategy based on estimating the real class relationships, so as to get the "best" CSDs in a completely automatic way. For the second stage, we propose a novel Decomposed Graph Prototype Network (DGPN) method, following the principles of locality and compositionality for zero-shot model generalization. Finally, we conduct extensive experiments to demonstrate the effectiveness of our solutions.

cs.AI↗

arXiv2020

IEEE 802.11be-Wi-Fi 7: New Challenges and Opportunities

With the emergence of 4k/8k video, the throughput requirement of video delivery will keep grow to tens of Gbps. Other new high-throughput and low-latency video applications including augmented reality (AR), virtual reality (VR), and online gaming, are also proliferating. Due to the related stringent requirements, supporting these applications over wireless local area network (WLAN) is far beyond the capabilities of the new WLAN standard -- IEEE 802.11ax. To meet these emerging demands, the IEEE 802.11 will release a new amendment standard IEEE 802.11be -- Extremely High Throughput (EHT), also known as Wireless-Fidelity (Wi-Fi) 7. This article provides the comprehensive survey on the key medium access control (MAC) layer techniques and physical layer (PHY) techniques being discussed in the EHT task group, including the channelization and tone plan, multiple resource units (multi-RU) support, 4096 quadrature amplitude modulation (4096-QAM), preamble designs, multiple link operations (e.g., multi-link aggregation and channel access), multiple input multiple output (MIMO) enhancement, multiple access point (multi-AP) coordination (e.g., multi-AP joint transmission), enhanced link adaptation and retransmission protocols (e.g., hybrid automatic repeat request (HARQ)). This survey covers both the critical technologies being discussed in EHT standard and the related latest progresses from worldwide research. Besides, the potential developments beyond EHT are discussed to provide some possible future research directions for WLAN.

eess.SP↗

arXiv2020

PANDA: A Gigapixel-level Human-centric Video Dataset

We present PANDA, the first gigaPixel-level humAN-centric viDeo dAtaset, for large-scale, long-term, and multi-object visual analysis. The videos in PANDA were captured by a gigapixel camera and cover real-world scenes with both wide field-of-view (~1 square kilometer area) and high-resolution details (~gigapixel-level/frame). The scenes may contain 4k head counts with over 100x scale variation. PANDA provides enriched and hierarchical ground-truth annotations, including 15,974.6k bounding boxes, 111.8k fine-grained attribute labels, 12.7k trajectories, 2.2k groups and 2.9k interactions. We benchmark the human detection and tracking tasks. Due to the vast variance of pedestrian pose, scale, occlusion and trajectory, existing approaches are challenged by both accuracy and efficiency. Given the uniqueness of PANDA with both wide FoV and high resolution, a new task of interaction-aware group detection is introduced. We design a 'global-to-local zoom-in' framework, where global trajectories and local interactions are simultaneously encoded, yielding promising results. We believe PANDA will contribute to the community of artificial intelligence and praxeology by understanding human behaviors and interactions in large-scale real-world scenes. PANDA Website: http://www.panda-dataset.com.

cs.CV↗

arXiv2020

A Systematic Review of Unsupervised Learning Techniques for Software Defect Prediction

Background: Unsupervised machine learners have been increasingly applied to software defect prediction. It is an approach that may be valuable for software practitioners because it reduces the need for labeled training data. Objective: Investigate the use and performance of unsupervised learning techniques in software defect prediction. Method: We conducted a systematic literature review that identified 49 studies containing 2456 individual experimental results, which satisfied our inclusion criteria published between January 2000 and March 2018. In order to compare prediction performance across these studies in a consistent way, we (re-)computed the confusion matrices and employed the Matthews Correlation Coefficient (MCC) as our main performance measure. Results: Our meta-analysis shows that unsupervised models are comparable with supervised models for both within-project and cross-project prediction. Among the 14 families of unsupervised model, Fuzzy CMeans (FCM) and Fuzzy SOMs (FSOMs) perform best. In addition, where we were able to check, we found that almost 11% (262/2456) of published results (contained in 16 papers) were internally inconsistent and a further 33% (823/2456) provided insufficient details for us to check. Conclusion: Although many factors impact the performance of a classifier, e.g., dataset characteristics, broadly speaking, unsupervised classifiers do not seem to perform worse than the supervised classifiers in our review. However, we note a worrying prevalence of (i) demonstrably erroneous experimental results, (ii) undemanding benchmarks and (iii) incomplete reporting. We therefore encourage researchers to be comprehensive in their reporting.

cs.SE↗

arXiv2019

Topic-aware chatbot using Recurrent Neural Networks and Nonnegative Matrix Factorization

We propose a novel model for a topic-aware chatbot by combining the traditional Recurrent Neural Network (RNN) encoder-decoder model with a topic attention layer based on Nonnegative Matrix Factorization (NMF). After learning topic vectors from an auxiliary text corpus via NMF, the decoder is trained so that it is more likely to sample response words from the most correlated topic vectors. One of the main advantages in our architecture is that the user can easily switch the NMF-learned topic vectors so that the chatbot obtains desired topic-awareness. We demonstrate our model by training on a single conversational data set which is then augmented with topic matrices learned from different auxiliary data sets. We show that our topic-aware chatbot not only outperforms the non-topic counterpart, but also that each topic-aware model qualitatively and contextually gives the most relevant answer depending on the topic of question.

cs.CL↗

arXiv2019

Global Sparse Momentum SGD for Pruning Very Deep Neural Networks

Deep Neural Network (DNN) is powerful but computationally expensive and memory intensive, thus impeding its practical usage on resource-constrained front-end devices. DNN pruning is an approach for deep model compression, which aims at eliminating some parameters with tolerable performance degradation. In this paper, we propose a novel momentum-SGD-based optimization method to reduce the network complexity by on-the-fly pruning. Concretely, given a global compression ratio, we categorize all the parameters into two parts at each training iteration which are updated using different rules. In this way, we gradually zero out the redundant parameters, as we update them using only the ordinary weight decay but no gradients derived from the objective function. As a departure from prior methods that require heavy human works to tune the layer-wise sparsity ratios, prune by solving complicated non-differentiable problems or finetune the model after pruning, our method is characterized by 1) global compression that automatically finds the appropriate per-layer sparsity ratios; 2) end-to-end training; 3) no need for a time-consuming re-training process after pruning; and 4) superior capability to find better winning tickets which have won the initialization lottery.

cs.LG↗