arXiv subjects

Bin Luo

Publications and source records attributed to Bin Luo.

At least 163 records · Page 9Linked to original sources

arXiv2023

ProContEXT: Exploring Progressive Context Transformer for Tracking

Existing Visual Object Tracking (VOT) only takes the target area in the first frame as a template. This causes tracking to inevitably fail in fast-changing and crowded scenes, as it cannot account for changes in object appearance between frames. To this end, we revamped the tracking framework with Progressive Context Encoding Transformer Tracker (ProContEXT), which coherently exploits spatial and temporal contexts to predict object motion trajectories. Specifically, ProContEXT leverages a context-aware self-attention module to encode the spatial and temporal context, refining and updating the multi-scale static and dynamic templates to progressively perform accurately tracking. It explores the complementary between spatial and temporal context, raising a new pathway to multi-context modeling for transformer-based trackers. In addition, ProContEXT revised the token pruning technique to reduce computational complexity. Extensive experiments on popular benchmark datasets such as GOT-10k and TrackingNet demonstrate that the proposed ProContEXT achieves state-of-the-art performance.

cs.CV↗

arXiv2023

LongShortNet: Exploring Temporal and Semantic Features Fusion in Streaming Perception

Streaming perception is a critical task in autonomous driving that requires balancing the latency and accuracy of the autopilot system. However, current methods for streaming perception are limited as they only rely on the current and adjacent two frames to learn movement patterns. This restricts their ability to model complex scenes, often resulting in poor detection results. To address this limitation, we propose LongShortNet, a novel dual-path network that captures long-term temporal motion and integrates it with short-term spatial semantics for real-time perception. LongShortNet is notable as it is the first work to extend long-term temporal modeling to streaming perception, enabling spatiotemporal feature fusion. We evaluate LongShortNet on the challenging Argoverse-HD dataset and demonstrate that it outperforms existing state-of-the-art methods with almost no additional computational cost.

cs.CV↗

arXiv2023

Judicial Intelligent Assistant System: Extracting Events from Divorce Cases to Detect Disputes for the Judge

In formal procedure of civil cases, the textual materials provided by different parties describe the development process of the cases. It is a difficult but necessary task to extract the key information for the cases from these textual materials and to clarify the dispute focus of related parties. Currently, officers read the materials manually and use methods, such as keyword searching and regular matching, to get the target information. These approaches are time-consuming and heavily depending on prior knowledge and carefulness of the officers. To assist the officers to enhance working efficiency and accuracy, we propose an approach to detect disputes from divorce cases based on a two-round-labeling event extracting technique in this paper. We implement the Judicial Intelligent Assistant (JIA) system according to the proposed approach to 1) automatically extract focus events from divorce case materials, 2) align events by identifying co-reference among them, and 3) detect conflicts among events brought by the plaintiff and the defendant. With the JIA system, it is convenient for judges to determine the disputed issues. Experimental results demonstrate that the proposed approach and system can obtain the focus of cases and detect conflicts more effectively and efficiently comparing with existing method.

cs.CL↗

arXiv2023

Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

Weakly Supervised Video Anomaly Detection (WSVAD) is challenging because the binary anomaly label is only given on the video level, but the output requires snippet-level predictions. So, Multiple Instance Learning (MIL) is prevailing in WSVAD. However, MIL is notoriously known to suffer from many false alarms because the snippet-level detector is easily biased towards the abnormal snippets with simple context, confused by the normality with the same bias, and missing the anomaly with a different pattern. To this end, we propose a new MIL framework: Unbiased MIL (UMIL), to learn unbiased anomaly features that improve WSVAD. At each MIL training iteration, we use the current detector to divide the samples into two groups with different context biases: the most confident abnormal/normal snippets and the rest ambiguous ones. Then, by seeking the invariant features across the two sample groups, we can remove the variant context biases. Extensive experiments on benchmarks UCF-Crime and TAD demonstrate the effectiveness of our UMIL. Our code is provided at https://github.com/ktr-hubrt/UMIL.

cs.CV↗

arXiv2023

MutualFormer: Multi-Modality Representation Learning via Cross-Diffusion Attention

Aggregating multi-modality data to obtain reliable data representation attracts more and more attention. Recent studies demonstrate that Transformer models usually work well for multi-modality tasks. Existing Transformers generally either adopt the Cross-Attention (CA) mechanism or simple concatenation to achieve the information interaction among different modalities which generally ignore the issue of modality gap. In this work, we re-think Transformer and extend it to MutualFormer for multi-modality data representation. Rather than CA in Transformer, MutualFormer employs our new design of Cross-Diffusion Attention (CDA) to conduct the information communication among different modalities. Comparing with CA, the main advantages of the proposed CDA are three aspects. First, the crossaffinities in CDA are defined based on the individual modality affinities in the metric space which thus can naturally avoid the issue of modality/domain gap in feature based CA definition. Second, CDA provides a general scheme which can either be used for multimodality representation or serve as the post-optimization for existing CA models. Third, CDA is implemented efficiently. We successfully apply the MutualFormer on different multi-modality learning tasks (i.e., RGB-Depth SOD, RGB-NIR object ReID). Extensive experiments demonstrate the effectiveness of the proposed MutualFormer.

cs.CV↗

arXiv2023

X-ray Unveiling Events in a z~1.6 Active Galactic Nucleus in the 7 Ms Chandra Deep Field-South

We investigate the extreme X-ray variability of a z = 1.608 active galactic nucleus in the 7 Ms Chandra Deep Field-South (XID 403), which showed two significant X-ray brightening events. In the first event, XID 403 brightened by a factor of $>2.5$ in $\lesssim6.1$ rest-frame days in the observed-frame 0.5-5 keV band. The event lasted for $\approx5.0\textrm{-}7.3$ days, and then XID 403 dimmed by a factor of $>6.0$ in $\lesssim6.1$ days. After $\approx1.1\textrm{-}2.5$ years in the rest frame (including long observational gaps), it brightened again with the 0.5-5 keV flux increasing by a factor of $>12.6$. The second event lasted over 251 days and the source remained bright until the end of the 7 Ms exposure. The spectrum is a steep power law (photon index $Γ=2.8\pm0.3$) without obscuration during the second outburst, and the rest-frame 2-10 keV luminosity reaches $1.5^{+0.8}_{-0.5}\times10^{43}$ erg s$^{-1}$; there is no significant spectral evolution within this epoch. The infrared-to-UV spectral energy distribution of XID 403 is dominated by the host galaxy. There is no significant optical/UV variability and $R$-band (rest-frame $\approx2500$ $\unicode{xC5}$) brightening contemporaneous with the X-ray brightening. The extreme X-ray variability is likely due to two X-ray unveiling events, where the line of sight to the corona is no longer shielded by high-density gas clumps in a small-scale dust-free absorber. XID 403 is probably a high-redshift analog of local narrow-line Seyfert 1 galaxies, and the X-ray absorber is a powerful accretion-disk wind. On the other hand, we cannot exclude the possibility that XID 403 is an unusual candidate for tidal disruption events.

astro-ph.HE↗

arXiv2023

CrossCodeBench: Benchmarking Cross-Task Generalization of Source Code Models

Despite the recent advances showing that a model pre-trained on large-scale source code data is able to gain appreciable generalization capability, it still requires a sizeable amount of data on the target task for fine-tuning. And the effectiveness of the model generalization is largely affected by the size and quality of the fine-tuning data, which is detrimental for target tasks with limited or unavailable resources. Therefore, cross-task generalization, with the goal of improving the generalization of the model to unseen tasks that have not been seen before, is of strong research and application value. In this paper, we propose a large-scale benchmark that includes 216 existing code-related tasks. Then, we annotate each task with the corresponding meta information such as task description and instruction, which contains detailed information about the task and a solution guide. This also helps us to easily create a wide variety of ``training/evaluation'' task splits to evaluate the various cross-task generalization capabilities of the model. Then we perform some preliminary experiments to demonstrate that the cross-task generalization of models can be largely improved by in-context learning methods such as few-shot learning and learning from task instructions, which shows the promising prospects of conducting cross-task learning research on our benchmark. We hope that the collection of the datasets and our benchmark will facilitate future work that is not limited to cross-task generalization.

cs.SE↗

arXiv2023

An Empirical Comparison of Pre-Trained Models of Source Code

While a large number of pre-trained models of source code have been successfully developed and applied to a variety of software engineering (SE) tasks in recent years, our understanding of these pre-trained models is arguably fairly limited. With the goal of advancing our understanding of these models, we perform the first systematic empirical comparison of 19 recently-developed pre-trained models of source code on 13 SE tasks. To gain additional insights into these models, we adopt a recently-developed 4-dimensional categorization of pre-trained models, and subsequently investigate whether there are correlations between different categories of pre-trained models and their performances on different SE tasks.

cs.SE↗

arXiv2023

Universal adversarial perturbation for remote sensing images

Recently, with the application of deep learning in the remote sensing image (RSI) field, the classification accuracy of the RSI has been dramatically improved compared with traditional technology. However, even the state-of-the-art object recognition convolutional neural networks are fooled by the universal adversarial perturbation (UAP). The research on UAP is mostly limited to ordinary images, and RSIs have not been studied. To explore the basic characteristics of UAPs of RSIs, this paper proposes a novel method combining an encoder-decoder network with an attention mechanism to generate the UAP of RSIs. Firstly, the former is used to generate the UAP, which can learn the distribution of perturbations better, and then the latter is used to find the sensitive regions concerned by the RSI classification model. Finally, the generated regions are used to fine-tune the perturbation making the model misclassified with fewer perturbations. The experimental results show that the UAP can make the classification model misclassify, and the attack success rate of our proposed method on the RSI data set is as high as 97.09%.

cs.CV↗

arXiv2022

Adversarial Example Defense via Perturbation Grading Strategy

Deep Neural Networks have been widely used in many fields. However, studies have shown that DNNs are easily attacked by adversarial examples, which have tiny perturbations and greatly mislead the correct judgment of DNNs. Furthermore, even if malicious attackers cannot obtain all the underlying model parameters, they can use adversarial examples to attack various DNN-based task systems. Researchers have proposed various defense methods to protect DNNs, such as reducing the aggressiveness of adversarial examples by preprocessing or improving the robustness of the model by adding modules. However, some defense methods are only effective for small-scale examples or small perturbations but have limited defense effects for adversarial examples with large perturbations. This paper assigns different defense strategies to adversarial perturbations of different strengths by grading the perturbations on the input examples. Experimental results show that the proposed method effectively improves defense performance. In addition, the proposed method does not modify any task model, which can be used as a preprocessing module, which significantly reduces the deployment cost in practical applications.

cs.CV↗

arXiv2022

Rethinking Batch Sample Relationships for Data Representation: A Batch-Graph Transformer based Approach

Exploring sample relationships within each mini-batch has shown great potential for learning image representations. Existing works generally adopt the regular Transformer to model the visual content relationships, ignoring the cues of semantic/label correlations between samples. Also, they generally adopt the "full" self-attention mechanism which are obviously redundant and also sensitive to the noisy samples. To overcome these issues, in this paper, we design a simple yet flexible Batch-Graph Transformer (BGFormer) for mini-batch sample representations by deeply capturing the relationships of image samples from both visual and semantic perspectives. BGFormer has three main aspects. (1) It employs a flexible graph model, termed Batch Graph to jointly encode the visual and semantic relationships of samples within each mini-batch. (2) It explores the neighborhood relationships of samples by borrowing the idea of sparse graph representation which thus performs robustly, w.r.t., noisy samples. (3) It devises a novel Transformer architecture that mainly adopts dual structure-constrained self-attention (SSA), together with graph normalization, FFN, etc, to carefully exploit the batch graph information for sample tokens (nodes) representations. As an application, we apply BGFormer to the metric learning tasks. Extensive experiments on four popular datasets demonstrate the effectiveness of the proposed model.

cs.CV↗

arXiv2022

Data Dimension Reduction makes ML Algorithms efficient

Data dimension reduction (DDR) is all about mapping data from high dimensions to low dimensions, various techniques of DDR are being used for image dimension reduction like Random Projections, Principal Component Analysis (PCA), the Variance approach, LSA-Transform, the Combined and Direct approaches, and the New Random Approach. Auto-encoders (AE) are used to learn end-to-end mapping. In this paper, we demonstrate that pre-processing not only speeds up the algorithms but also improves accuracy in both supervised and unsupervised learning. In pre-processing of DDR, first PCA based DDR is used for supervised learning, then we explore AE based DDR for unsupervised learning. In PCA based DDR, we first compare supervised learning algorithms accuracy and time before and after applying PCA. Similarly, in AE based DDR, we compare unsupervised learning algorithm accuracy and time before and after AE representation learning. Supervised learning algorithms including support-vector machines (SVM), Decision Tree with GINI index, Decision Tree with entropy and Stochastic Gradient Descent classifier (SGDC) and unsupervised learning algorithm including K-means clustering, are used for classification purpose. We used two datasets MNIST and FashionMNIST Our experiment shows that there is massive improvement in accuracy and time reduction after pre-processing in both supervised and unsupervised learning.

cs.CV↗

arXiv2022

Efficient and Fine-grained Redactable Blockchain Supporting Accountability and Updating Policies

Redactable Blockchain aims to ensure immutability of the data for most of appications, and provide authorized mutability for some specific applications such as removing illegal content from blockchains. However, the existing redactable blockchain scheme has low redacting efficiency, and lacks an accountable and updatable fine-grained mechanism to control redacting rights. To solve the above problems, we propose an efficient and fine-grained redactable blockchain scheme with accountability and updatable policies. In our scheme, the transaction owner can set the updatable policy associated with the transaction, and only users who meet the policy can become the redactor of the transaction. In order to prevent redactors from abusing redacting right, we introduce the concept of a witness group. A redacted transaction is legal if and only if it contains the signatures of redactor and witness group. We first give the concept of witness group, and then show the proposed scheme. Finally, we demonstrate that scheme is feasible and efficient through a series of experiments and analysis.

cs.CR↗

arXiv2022

ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding

Recent years have witnessed the rise and success of pre-training techniques in visually-rich document understanding. However, most existing methods lack the systematic mining and utilization of layout-centered knowledge, leading to sub-optimal performances. In this paper, we propose ERNIE-Layout, a novel document pre-training solution with layout knowledge enhancement in the whole workflow, to learn better representations that combine the features from text, layout, and image. Specifically, we first rearrange input sequences in the serialization stage, and then present a correlative pre-training task, reading order prediction, to learn the proper reading order of documents. To improve the layout awareness of the model, we integrate a spatial-aware disentangled attention into the multi-modal transformer and a replaced regions prediction task into the pre-training phase. Experimental results show that ERNIE-Layout achieves superior performance on various downstream tasks, setting new state-of-the-art on key information extraction, document image classification, and document question answering datasets. The code and models are publicly available at http://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-layout.

cs.CL↗

arXiv2022

Cost-effective photonic super-resolution millimeter-wave joint radar-communication system using self-coherent detection

A cost-effective millimeter-wave (MMW) joint radar-communication (JRC) system with super resolution is proposed and experimentally demonstrated, using optical heterodyne up-conversion and self-coherent detection down-conversion techniques. The point lies in the designed coherent dual-band constant envelope linear frequency modulation-orthogonal frequency division multiplexing (LFM-OFDM) signal with opposite phase modulation indexes for the JRC system. Then the self-coherent detection, as a simple and low-cost means, is accordingly facilitated for both de-chirping of MMW radar and frequency down-conversion reception of MMW communication, which circumvents the costly high-speed mixers along with MMW local oscillators and more significantly achieves the real-time decomposition of radar and communication information. Furthermore, a super resolution radar range profile is realized through the coherent fusion processing of dual-band JRC signal. In experiments, a dual-band LFM-OFDM JRC signal centered at 54-GHz and 61-GHz is generated. The dual bands are featured with an identical instantaneous bandwidth of 2 GHz and carry an OFDM signal of 1 GBaud, which help to achieve a 6-Gbit/s data rate for communication and a 1.76-cm range resolution for radar.

eess.SP↗

arXiv2022

Neural Program Repair: Systems, Challenges and Solutions

Automated Program Repair (APR) aims to automatically fix bugs in the source code. Recently, as advances in Deep Learning (DL) field, there is a rise of Neural Program Repair (NPR) studies, which formulate APR as a translation task from buggy code to correct code and adopt neural networks based on encoder-decoder architecture. Compared with other APR techniques, NPR approaches have a great advantage in applicability because they do not need any specification (i.e., a test suite). Although NPR has been a hot research direction, there isn't any overview on this field yet. In order to help interested readers understand architectures, challenges and corresponding solutions of existing NPR systems, we conduct a literature review on latest studies in this paper. We begin with introducing the background knowledge on this field. Next, to be understandable, we decompose the NPR procedure into a series of modules and explicate various design choices on each module. Furthermore, we identify several challenges and discuss the effect of existing solutions. Finally, we conclude and provide some promising directions for future research.

cs.SE↗

arXiv2022

ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding

Recent efforts of multimodal Transformers have improved Visually Rich Document Understanding (VrDU) tasks via incorporating visual and textual information. However, existing approaches mainly focus on fine-grained elements such as words and document image patches, making it hard for them to learn from coarse-grained elements, including natural lexical units like phrases and salient visual regions like prominent image regions. In this paper, we attach more importance to coarse-grained elements containing high-density information and consistent semantics, which are valuable for document understanding. At first, a document graph is proposed to model complex relationships among multi-grained multimodal elements, in which salient visual regions are detected by a cluster-based method. Then, a multi-grained multimodal Transformer called mmLayout is proposed to incorporate coarse-grained information into existing pre-trained fine-grained multimodal Transformers based on the graph. In mmLayout, coarse-grained information is aggregated from fine-grained, and then, after further processing, is fused back into fine-grained for final prediction. Furthermore, common sense enhancement is introduced to exploit the semantic information of natural lexical units. Experimental results on four tasks, including information extraction and document question answering, show that our method can improve the performance of multimodal Transformers based on fine-grained elements and achieve better performance with fewer parameters. Qualitative analyses show that our method can capture consistent semantics in coarse-grained elements.

cs.CV↗

arXiv2022

SQL and NoSQL Databases Software architectures performance analysis and assessments -- A Systematic Literature review

Context: The efficient processing of Big Data is a challenging task for SQL and NoSQL Databases, where competent software architecture plays a vital role. The SQL Databases are designed for structuring data and supporting vertical scalability. In contrast, horizontal scalability is backed by NoSQL Databases and can process sizeable unstructured Data efficiently. One can choose the right paradigm according to the organisation's needs; however, making the correct choice can often be challenging. The SQL and NoSQL Databases follow different architectures. Also, the mixed model is followed by each category of NoSQL Databases. Hence, data movement becomes difficult for cloud consumers across multiple cloud service providers (CSPs). In addition, each cloud platform IaaS, PaaS, SaaS, and DBaaS also monitors various paradigms. Objective: This systematic literature review (SLR) aims to study the related articles associated with SQL and NoSQL Database software architectures and tackle data portability and Interoperability among various cloud platforms. State of the art presented many performance comparison studies of SQL and NoSQL Databases by observing scaling, performance, availability, consistency and sharding characteristics. According to the research studies, NoSQL Database designed structures can be the right choice for big data analytics, while SQL Databases are suitable for OLTP Databases. The researcher proposes numerous approaches associated with data movement in the cloud. Platform-based APIs are developed, which makes users' data movement difficult. Therefore, data portability and Interoperability issues are noticed during data movement across multiple CSPs. To minimize developer efforts and Interoperability, Unified APIs are demanded to make data movement relatively more accessible among various cloud platforms.

cs.DB↗