Searcharxiv⌕ Search

arXiv subjects

Bin Luo

Publications and source records attributed to Bin Luo.

At least 145 records · Page 8Linked to original sources
arXiv2023

Practical Program Repair via Preference-based Ensemble Strategy

To date, over 40 Automated Program Repair (APR) tools have been designed with varying bug-fixing strategies, which have been demonstrated to have complementary performance in terms of being effective for different bug classes. Intuitively, it should be feasible to improve the overall bug-fixing performance of APR via assembling existing tools. Unfortunately, simply invoking all available APR tools for a given bug can result in unacceptable costs on APR execution as well as on patch validation (via expensive testing). Therefore, while assembling existing tools is appealing, it requires an efficient strategy to reconcile the need to fix more bugs and the requirements for practicality. In light of this problem, we propose a Preference-based Ensemble Program Repair framework (P-EPR), which seeks to effectively rank APR tools for repairing different bugs. P-EPR is the first non-learning-based APR ensemble method that is novel in its exploitation of repair patterns as a major source of knowledge for ranking APR tools and its reliance on a dynamic update strategy that enables it to immediately exploit and benefit from newly derived repair results. Experimental results show that P-EPR outperforms existing strategies significantly both in flexibility and effectiveness.

cs.SE↗
arXiv2023

FAIR: Flow Type-Aware Pre-Training of Compiler Intermediate Representations

While the majority of existing pre-trained models from code learn source code features such as code tokens and abstract syntax trees, there are some other works that focus on learning from compiler intermediate representations (IRs). Existing IR-based models typically utilize IR features such as instructions, control and data flow graphs (CDFGs), call graphs, etc. However, these methods confuse variable nodes and instruction nodes in a CDFG and fail to distinguish different types of flows, and the neural networks they use fail to capture long-distance dependencies and have over-smoothing and over-squashing problems. To address these weaknesses, we propose FAIR, a Flow type-Aware pre-trained model for IR that involves employing (1) a novel input representation of IR programs; (2) Graph Transformer to address over-smoothing, over-squashing and long-dependencies problems; and (3) five pre-training tasks that we specifically propose to enable FAIR to learn the semantics of IR tokens, flow type information, and the overall representation of IR. Experimental results show that FAIR can achieve state-of-the-art results on four code-related downstream tasks.

cs.SE↗
arXiv2023

Pedestrian Attribute Recognition: A Survey

Recognizing pedestrian attributes is an important task in the computer vision community due to it plays an important role in video surveillance. Many algorithms have been proposed to handle this task. The goal of this paper is to review existing works using traditional methods or based on deep learning networks. Firstly, we introduce the background of pedestrian attribute recognition (PAR, for short), including the fundamental concepts of pedestrian attributes and corresponding challenges. Secondly, we introduce existing benchmarks, including popular datasets and evaluation criteria. Thirdly, we analyze the concept of multi-task learning and multi-label learning and also explain the relations between these two learning algorithms and pedestrian attribute recognition. We also review some popular network architectures which have been widely applied in the deep learning community. Fourthly, we analyze popular solutions for this task, such as attributes group, part-based, etc. Fifthly, we show some applications that take pedestrian attributes into consideration and achieve better performance. Finally, we summarize this paper and give several possible research directions for pedestrian attribute recognition. We continuously update the following GitHub to keep tracking the most cutting-edge related works on pedestrian attribute recognition~\url{https://github.com/wangxiao5791509/Pedestrian-Attribute-Recognition-Paper-List}

cs.CV↗
arXiv2023

Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning

Depth-aware panoptic segmentation is an emerging topic in computer vision which combines semantic and geometric understanding for more robust scene interpretation. Recent works pursue unified frameworks to tackle this challenge but mostly still treat it as two individual learning tasks, which limits their potential for exploring cross-domain information. We propose a deeply unified framework for depth-aware panoptic segmentation, which performs joint segmentation and depth estimation both in a per-segment manner with identical object queries. To narrow the gap between the two tasks, we further design a geometric query enhancement method, which is able to integrate scene geometry into object queries using latent representations. In addition, we propose a bi-directional guidance learning approach to facilitate cross-task feature learning by taking advantage of their mutual relations. Our method sets the new state of the art for depth-aware panoptic segmentation on both Cityscapes-DVPS and SemKITTI-DVPS datasets. Moreover, our guidance learning approach is shown to deliver performance improvement even under incomplete supervision labels.

cs.CV↗
arXiv2023

Tracking Anything in High Quality

Visual object tracking is a fundamental video task in computer vision. Recently, the notably increasing power of perception algorithms allows the unification of single/multiobject and box/mask-based tracking. Among them, the Segment Anything Model (SAM) attracts much attention. In this report, we propose HQTrack, a framework for High Quality Tracking anything in videos. HQTrack mainly consists of a video multi-object segmenter (VMOS) and a mask refiner (MR). Given the object to be tracked in the initial frame of a video, VMOS propagates the object masks to the current frame. The mask results at this stage are not accurate enough since VMOS is trained on several closeset video object segmentation (VOS) datasets, which has limited ability to generalize to complex and corner scenes. To further improve the quality of tracking masks, a pretrained MR model is employed to refine the tracking results. As a compelling testament to the effectiveness of our paradigm, without employing any tricks such as test-time data augmentations and model ensemble, HQTrack ranks the 2nd place in the Visual Object Tracking and Segmentation (VOTS2023) challenge. Code and models are available at https://github.com/jiawen-zhu/HQTrack.

cs.CV↗
arXiv2023

XMM-Newton Observations of Two Archival X-ray Weak Type 1 Quasars: Obscuration Induced X-ray Weakness and Variability

We report \hbox{XMM-Newton} observations of two examples of an unclassified type of \hbox{X-ray} weak quasars from the \citet{2020ApJ...900..141P} survey of \hbox{X-ray} weak quasars in the Chandra archive, SDSS J083116.62+321329.6 at $z=1.797$ and SDSS J142339.87+042041.1 at $z=1.702$. They do not belong to the known populations of \hbox{X-ray} weak quasars that show broad absorption lines, weak ultraviolet (UV) broad emission lines, or red optical/UV continua. Instead, they display typical quasar UV spectra and spectral energy distributions. In the \hbox{XMM-Newton} observations, both quasars show nominal levels of \hbox{X-ray} emission with typical quasar \hbox{X-ray} spectral shapes (\hbox{power-law} photon indices of $1.99^{+0.27}_{-0.23}$ and $1.86^{+0.15}_{-0.14}$), displaying strong \hbox{X-ray} variability compared to the archival Chandra data (variability factors of $4.0^{+1.6}_{-1.4}$ and $9.0^{+7.4}_{-3.8}$ in terms of the 2 keV flux density). Simultaneous optical (rest-frame UV) spectra indicate no strong variability compared to the archival spectra. Long-term optical/UV and infrared light curves do not show any substantial variability either. We consider that the \hbox{X-ray} weakness observed in the Chandra data is due to \hbox{X-ray} obscuration from a small-scale dust-free absorber, likely related to accretion-disk winds. Such \hbox{X-ray} weak/absorbed states are probably rare in typical quasars, and thus both targets recovered to \hbox{X-ray} nominal-strength states in the \hbox{XMM-Newton} observations.

astro-ph.GA↗
arXiv2023

Communication Resources Constrained Hierarchical Federated Learning for End-to-End Autonomous Driving

While federated learning (FL) improves the generalization of end-to-end autonomous driving by model aggregation, the conventional single-hop FL (SFL) suffers from slow convergence rate due to long-range communications among vehicles and cloud server. Hierarchical federated learning (HFL) overcomes such drawbacks via introduction of mid-point edge servers. However, the orchestration between constrained communication resources and HFL performance becomes an urgent problem. This paper proposes an optimization-based Communication Resource Constrained Hierarchical Federated Learning (CRCHFL) framework to minimize the generalization error of the autonomous driving model using hybrid data and model aggregation. The effectiveness of the proposed CRCHFL is evaluated in the Car Learning to Act (CARLA) simulation platform. Results show that the proposed CRCHFL both accelerates the convergence rate and enhances the generalization of federated learning autonomous driving model. Moreover, under the same communication resource budget, it outperforms the HFL by 10.33% and the SFL by 12.44%.

cs.RO↗
arXiv2023

Backdooring Neural Code Search

Reusing off-the-shelf code snippets from online repositories is a common practice, which significantly enhances the productivity of software developers. To find desired code snippets, developers resort to code search engines through natural language queries. Neural code search models are hence behind many such engines. These models are based on deep learning and gain substantial attention due to their impressive performance. However, the security aspect of these models is rarely studied. Particularly, an adversary can inject a backdoor in neural code search models, which return buggy or even vulnerable code with security/privacy issues. This may impact the downstream software (e.g., stock trading systems and autonomous driving) and cause financial loss and/or life-threatening incidents. In this paper, we demonstrate such attacks are feasible and can be quite stealthy. By simply modifying one variable/function name, the attacker can make buggy/vulnerable code rank in the top 11%. Our attack BADCODE features a special trigger generation and injection procedure, making the attack more effective and stealthy. The evaluation is conducted on two neural code search models and the results show our attack outperforms baselines by 60%. Our user study demonstrates that our attack is more stealthy than the baseline by two times based on the F1 score.

cs.SE↗
arXiv2023

Learning the Relation between Similarity Loss and Clustering Loss in Self-Supervised Learning

Self-supervised learning enables networks to learn discriminative features from massive data itself. Most state-of-the-art methods maximize the similarity between two augmentations of one image based on contrastive learning. By utilizing the consistency of two augmentations, the burden of manual annotations can be freed. Contrastive learning exploits instance-level information to learn robust features. However, the learned information is probably confined to different views of the same instance. In this paper, we attempt to leverage the similarity between two distinct images to boost representation in self-supervised learning. In contrast to instance-level information, the similarity between two distinct images may provide more useful information. Besides, we analyze the relation between similarity loss and feature-level cross-entropy loss. These two losses are essential for most deep learning methods. However, the relation between these two losses is not clear. Similarity loss helps obtain instance-level representation, while feature-level cross-entropy loss helps mine the similarity between two distinct images. We provide theoretical analyses and experiments to show that a suitable combination of these two losses can get state-of-the-art results. Code is available at https://github.com/guijiejie/ICCL.

cs.CV↗
arXiv2023

HDFormer: High-order Directed Transformer for 3D Human Pose Estimation

Human pose estimation is a challenging task due to its structured data sequence nature. Existing methods primarily focus on pair-wise interaction of body joints, which is insufficient for scenarios involving overlapping joints and rapidly changing poses. To overcome these issues, we introduce a novel approach, the High-order Directed Transformer (HDFormer), which leverages high-order bone and joint relationships for improved pose estimation. Specifically, HDFormer incorporates both self-attention and high-order attention to formulate a multi-order attention module. This module facilitates first-order "joint$\leftrightarrow$joint", second-order "bone$\leftrightarrow$joint", and high-order "hyperbone$\leftrightarrow$joint" interactions, effectively addressing issues in complex and occlusion-heavy situations. In addition, modern CNN techniques are integrated into the transformer-based architecture, balancing the trade-off between performance and efficiency. HDFormer significantly outperforms state-of-the-art (SOTA) models on Human3.6M and MPI-INF-3DHP datasets, requiring only 1/10 of the parameters and significantly lower computational costs. Moreover, HDFormer demonstrates broad real-world applicability, enabling real-time, accurate 3D pose estimation. The source code is in https://github.com/hyer/HDFormer

cs.CV↗
arXiv2023

DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving

Real-time perception, or streaming perception, is a crucial aspect of autonomous driving that has yet to be thoroughly explored in existing research. To address this gap, we present DAMO-StreamNet, an optimized framework that combines recent advances from the YOLO series with a comprehensive analysis of spatial and temporal perception mechanisms, delivering a cutting-edge solution. The key innovations of DAMO-StreamNet are (1) A robust neck structure incorporating deformable convolution, enhancing the receptive field and feature alignment capabilities (2) A dual-branch structure that integrates short-path semantic features and long-path temporal features, improving motion state prediction accuracy. (3) Logits-level distillation for efficient optimization, aligning the logits of teacher and student networks in semantic space. (4) A real-time forecasting mechanism that updates support frame features with the current frame, ensuring seamless streaming perception during inference. Our experiments demonstrate that DAMO-StreamNet surpasses existing state-of-the-art methods, achieving 37.8% (normal size (600, 960)) and 43.3% (large size (1200, 1920)) sAP without using extra data. This work not only sets a new benchmark for real-time perception but also provides valuable insights for future research. Additionally, DAMO-StreamNet can be applied to various autonomous systems, such as drones and robots, paving the way for real-time perception. The code is at https://github.com/zhiqic/DAMO-StreamNet.

cs.CV↗
arXiv2023

Adversarial Examples Detection with Enhanced Image Difference Features based on Local Histogram Equalization

Deep Neural Networks (DNNs) have recently made significant progress in many fields. However, studies have shown that DNNs are vulnerable to adversarial examples, where imperceptible perturbations can greatly mislead DNNs even if the full underlying model parameters are not accessible. Various defense methods have been proposed, such as feature compression and gradient masking. However, numerous studies have proven that previous methods create detection or defense against certain attacks, which renders the method ineffective in the face of the latest unknown attack methods. The invisibility of adversarial perturbations is one of the evaluation indicators for adversarial example attacks, which also means that the difference in the local correlation of high-frequency information in adversarial examples and normal examples can be used as an effective feature to distinguish the two. Therefore, we propose an adversarial example detection framework based on a high-frequency information enhancement strategy, which can effectively extract and amplify the feature differences between adversarial examples and normal examples. Experimental results show that the feature augmentation module can be combined with existing detection models in a modular way under this framework. Improve the detector's performance and reduce the deployment cost without modifying the existing detection model.

cs.CV↗
arXiv2023

Robust image steganography against lossy JPEG compression based on embedding domain selection and adaptive error correction

Transmitting images for communication on social networks has become routine, which is helpful for covert communication. The traditional steganography algorithm is unable to successfully convey secret information since the social network channel will perform lossy operations on images, such as JPEG compression. Previous studies tried to solve this problem by enhancing the robustness or making the cover adapt to the channel processing. In this study, we proposed a robust image steganography method against lossy JPEG compression based on embedding domain selection and adaptive error correction. To improve anti-steganalysis performance, the embedding domain is selected adaptively. To increase robustness and lessen the impact on anti-steganalysis performance, the error correction capacity of the error correction code is adaptively adjusted to eliminate redundancy. The experimental results show that the proposed method achieves better anti-steganalysis and robustness.

cs.MM↗
arXiv2023

Identification and Characterization of a Large Sample of Distant Active Dwarf Galaxies in XMM-SERVS

Active dwarf galaxies are important because they contribute to the evolution of dwarf galaxies and can reveal their hosted massive black holes. However, the sample size of such sources beyond the local universe is still highly limited. In this work, we search for active dwarf galaxies in the recently completed XMM-Spitzer Extragalactic Representative Volume Survey (XMM-SERVS). XMM-SERVS is currently the largest medium-depth X-ray survey covering 13 $\mathrm{deg}^2$ in three extragalactic fields, which all have well-characterized multi-wavelength information. After considering several factors that may lead to misidentifications, we identify 73 active dwarf galaxies at $z<1$, which constitutes the currently largest X-ray-selected sample beyond the local universe. Our sources are generally less obscured than predictions based on the massive-AGN (active galactic nucleus) X-ray luminosity function and have a low radio-excess fraction. We find that our sources reside in similar environments to inactive dwarf galaxies. We further quantify the accretion distribution of the dwarf-galaxy population after considering various selection effects and find that it decreases with X-ray luminosity, but redshift evolution cannot be statistically confirmed. Depending upon how we define an AGN, the active fraction may or may not show a strong dependence on stellar mass. Their Eddington ratios and X-ray bolometric corrections significantly deviate from the expected relation, which is likely caused by several large underlying systematic biases when estimating the relevant parameters for dwarf galaxies. Throughout this work, we also highlight problems in reliably measuring photometric redshifts and overcoming strong selection effects for distant active dwarf galaxies.

astro-ph.GA↗
arXiv2023

Radio AGN Selection and Characterization in Three Deep-Drilling Fields of the Vera C. Rubin Observatory Legacy Survey of Space and Time

The Australia Telescope Large Area Survey (ATLAS) and the VLA survey in the XMM-LSS/VIDEO deep field provide deep ($\approx 15$ $μ$Jybeam$^{-1}$) and high-resolution ($\approx$ 4.5--8 arcsec) radio coverage of the three XMM-SERVS fields (W-CDF-S, ELAIS-S1, and XMM-LSS). These data cover a total sky area of 11.3 deg$^2$ and contain $\approx 11000$ radio components. Furthermore, about 3~deg$^2$ of the XMM-LSS field also has deeper MIGHTEE data that achieve a median RMS of 5.6 $μ$Jy beam$^{-1}$ and detect more than 20000 radio sources. We analyze all these radio data and find source counterparts at other wavebands utilizing deep optical and IR surveys. The nature of these radio sources is studied using radio-band properties (spectral slope and morphology), and the IR-radio correlation. %and spectral energy distribution. Radio AGNs are selected and compared with those selected using other methods (e.g. X-ray). We found 1656 new AGNs that were not selected using X-ray and/or MIR methods. We constrain the FIR-to-UV SEDs of radio AGNs using {\sc cigale} and investigate the dependence of radio AGN fraction upon galaxy stellar mass and star-formation rate.

astro-ph.GA↗
arXiv2023

Strong and Rapid X-ray Variability of the Super-Eddington Accreting Quasar SDSS J081456.10+532533.5

We report strong and rapid X-ray variability found from the super-Eddington accreting quasar SDSS J081456.10+532533.5 at $z=0.1197$. It has a black-hole mass of $2.7\times10^{7}{M_{\odot}}$ and a dimensionless accretion rate of $\approx4$ measured from reverberation-mapping observations. It showed weak X-ray emission in the 2021 February Chandra observation, with the 2 keV flux density being $9.6^{+11.6}_{-4.6}$ times lower compared to an archival Swift observation. The 2 keV flux density is also $11.7^{+9.6}_{-6.3}$ times weaker compared to the expectation from its optical/UV emission. In a follow-up XMM-Newton observation 32 days later, the 2 keV flux density increased by a factor of $5.3^{+6.4}_{-2.4}$, and the spectra are best described by a power law modified with partial-covering absorption; the absorption-corrected intrinsic continuum is at a nominal flux level. Nearly simultaneous optical spectra reveal no variability, and there is only mild long-term optical/infrared variability from archival data (with a maximum variability amplitude of $\approx50\%$). We interpret the X-ray variability with an obscuration scenario, where the intrinsic X-ray continuum does not vary but the absorber has variable column density and covering factor along the line of sight. The absorber is likely the small-scale clumpy accretion wind that has been proposed to be responsible for similar X-ray variability in other super-Eddington accreting quasars.

astro-ph.HE↗
arXiv2023

The Most Obscured AGNs in the XMM-SERVS Fields

We perform X-ray spectral analyses to derive characteristics (e.g., column density, X-ray luminosity) of $\approx$10,200 active galactic nuclei (AGNs) in the XMM-Spitzer Extragalactic Representative Volume Survey (XMM-SERVS), which was designed to investigate the growth of supermassive black holes across a wide dynamic range of cosmic environments. Using physical torus models (e.g., Borus02) and a Bayesian approach, we uncover 22 representative Compton-thick (CT; $N_{\rm H} \;>\; 1.5\times10^{24}\; \rm cm^{-2}$) AGN candidates with good signal-to-noise ratios as well as a large sample of 136 heavily obscured AGNs. We also find an increasing CT fraction (\fct ) from low ($z<0.75$) to high ($z>0.75$) redshift. Our CT candidates tend to show hard X-ray spectral shapes and dust extinction in their SED fits, which may shed light on the connection between AGN obscuration and host-galaxy evolution.

astro-ph.GA↗
arXiv2023

Shedding New Light on Weak Emission-Line Quasars in the C$_{\rm IV}$-H$β$ Parameter Space

Weak emission-line quasars (WLQs) are a subset of Type 1 quasars that exhibit extremely weak Ly$α+$N V $λ$1240 and/or C IV $λ$1549 emission lines. We investigate the relationship between emission-line properties and accretion rate for a sample of 230 `ordinary' Type 1 quasars and 18 WLQs at $z < 0.5$ and $1.5 < z < 3.5$ that have rest-frame ultraviolet and optical spectral measurements. We apply a correction to the H$β$-based black-hole mass ($M_{\rm BH}$) estimates of these quasars using the strength of the optical Fe II emission. We confirm previous findings that WLQs' $M_{\rm BH}$ values are overestimated by up to an order of magnitude using the traditional broad emission-line region size-luminosity relation. With this $M_{\rm BH}$ correction, we find a significant correlation between H$β$-based Eddington luminosity ratios and a combination of the rest-frame C IV equivalent width and C IV blueshift with respect to the systemic redshift. This correlation holds for both ordinary quasars and WLQs, which suggests that the two-dimensional C IV parameter space can serve as an indicator of accretion rate in all Type 1 quasars across a wide range of spectral properties.

astro-ph.GA↗