Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

Research Collection School Of Computing and Information Systems

Discipline
Keyword
Publication Year
File Type

Articles 1561 - 1590 of 8692

Full-Text Articles in Entire DC Network

Partial Annotation-Based Video Moment Retrieval Via Iterative Learning, Wei Ji, Renjie Liang, Lizi Liao, Hao Fei, Fuli Feng Nov 2023

Partial Annotation-Based Video Moment Retrieval Via Iterative Learning, Wei Ji, Renjie Liang, Lizi Liao, Hao Fei, Fuli Feng

Research Collection School Of Computing and Information Systems

Given a descriptive language query, Video Moment Retrieval (VMR) aims to seek the corresponding semantic-consistent moment clip in the video, which is represented as a pair of the start and end timestamps. Although current methods have achieved satisfying performance, training these models heavily relies on the fully-annotated VMR datasets. Nonetheless, precise video temporal annotations are extremely labor-intensive and ambiguous due to the diverse preferences of different annotators.Although there are several works trying to explore weakly supervised VMR tasks with scattered annotated frames as labels, there is still much room to improve in terms of accuracy. Therefore, we design a new …

Go to article

Verifytl: Secure And Verifiable Collaborative Transfer Learning, Zhuoran Ma, Jianfeng Ma, Yinbin Miao, Ximeng Liu, Wei Zheng, Kim-Kwang Raymond Choo, Robert H. Deng Nov 2023

Verifytl: Secure And Verifiable Collaborative Transfer Learning, Zhuoran Ma, Jianfeng Ma, Yinbin Miao, Ximeng Liu, Wei Zheng, Kim-Kwang Raymond Choo, Robert H. Deng

Research Collection School Of Computing and Information Systems

Getting access to labeled datasets in certain sensitive application domains can be challenging. Hence, one may resort to transfer learning to transfer knowledge learned from a source domain with sufficient labeled data to a target domain with limited labeled data. However, most existing transfer learning techniques only focus on one-way transfer which may not benefit the source domain. In addition, there is the risk of a malicious adversary corrupting a number of domains, which can consequently result in inaccurate prediction or privacy leakage. In this paper, we construct a secure and Verif iable collaborative T ransfer L earning scheme, VerifyTL, …

Go to article

Autolog: A Log Sequence Synthesis Framework For Anomaly Detection, Yintong Huo, Yichen Li, Yuxin Su, Pinjia He, Zifan Xie, R. Michael Lyu Nov 2023

Autolog: A Log Sequence Synthesis Framework For Anomaly Detection, Yintong Huo, Yichen Li, Yuxin Su, Pinjia He, Zifan Xie, R. Michael Lyu

Research Collection School Of Computing and Information Systems

The rapid progress of modern computing systems has led to a growing interest in informative run-time logs. Various log-based anomaly detection techniques have been proposed to ensure software reliability. However, their implementation in the industry has been limited due to the lack of high-quality public log resources as training datasets.While some log datasets are available for anomaly detection, they suffer from limitations in (1) comprehensiveness of log events; (2) scalability over diverse systems; and (3) flexibility of log utility. To address these limitations, we propose AutoLog, the first automated log generation methodology for anomaly detection. AutoLog uses program analysis to …

Go to article

Cgt-Gan: Clip-Guided Text Gan For Image Captioning, Jiarui Yu, Haoran Li, Yanbin Hao, Bin Zhu, Tong Xu, Xiangnan He Nov 2023

Cgt-Gan: Clip-Guided Text Gan For Image Captioning, Jiarui Yu, Haoran Li, Yanbin Hao, Bin Zhu, Tong Xu, Xiangnan He

Research Collection School Of Computing and Information Systems

The large-scale visual-language pre-trained model, Contrastive Language-Image Pre-training (CLIP), has significantly improved image captioning for scenarios without human-annotated image-caption pairs. Recent advanced CLIP-based image captioning without human annotations follows a text-only training paradigm, i.e., reconstructing text from shared embedding space. Nevertheless, these approaches are limited by the training/inference gap or huge storage requirements for text embeddings. Given that it is trivial to obtain images in the real world, we propose CLIP-guided text GAN (CgT-GAN), which incorporates images into the training process to enable the model to "see" real visual modality. Particularly, we use adversarial training to teach CgT-GAN to mimic …

Go to article

Multimodal Fashion Knowledge Extraction As Captioning, Yifei Yuan, Wenxuan Zhang, Yang Deng, Wai Lam Nov 2023

Multimodal Fashion Knowledge Extraction As Captioning, Yifei Yuan, Wenxuan Zhang, Yang Deng, Wai Lam

Research Collection School Of Computing and Information Systems

Social media plays a significant role in boosting the fashion industry, where a massive amount of fashion-related posts are generated every day. In order to obtain the rich fashion information from the posts, we study the task of social media fashion knowledge extraction. Fashion knowledge, which typically consists of the occasion, person attributes, and fashion item information, can be effectively represented as a set of tuples. Most previous studies on fashion knowledge extraction are based on the fashion product images without considering the rich text information in social media posts. Existing work on fashion knowledge extraction in social media is …

Go to article

Toward Intention Discovery For Early Malice Detection In Cryptocurrency, Ling Cheng, Feida Zhu, Yong Wang, Ruicheng Liang, Huiwen Liu Oct 2023

Toward Intention Discovery For Early Malice Detection In Cryptocurrency, Ling Cheng, Feida Zhu, Yong Wang, Ruicheng Liang, Huiwen Liu

Research Collection School Of Computing and Information Systems

Cryptocurrency’s pseudo-anonymous nature makes it vulnerable to malicious activities. However, existing deep learning solutions lack interpretability and only support retrospective analysis of specific malice types. To address these challenges, we propose Intention-Monitor for early malice detection in Bitcoin. Our model, utilizing Decision-Tree based feature Selection and Complement (DT-SC), builds different feature sets for different malice types. The Status Proposal Module (SPM) and hierarchical self-attention predictor provide real-time global status and address label predictions. A survival module determines the stopping point and proposes the status sequence (intention). Our model detects various malicious activities with strong interpretability, outperforming state-of-the-art methods in extensive …

Go to article

The Future Can't Help Fix The Past: Assessing Program Repair In The Wild, Vinay Kabadi, Dezhen Kong, Siyu Xie, Lingfeng Bao, Gede Artha Azriadi Prana, Tien Duy B. Le, Xuan Bach D. Le, David Lo Oct 2023

The Future Can't Help Fix The Past: Assessing Program Repair In The Wild, Vinay Kabadi, Dezhen Kong, Siyu Xie, Lingfeng Bao, Gede Artha Azriadi Prana, Tien Duy B. Le, Xuan Bach D. Le, David Lo

Research Collection School Of Computing and Information Systems

Automated program repair (APR) has been gaining ground with substantial effort devoted to the area, opening up many challenges and opportunities. One such challenge is that the state-of-the-art repair techniques often resort to incomplete specifications, e.g., test cases that witness buggy behavior, to generate repairs. In practice, bug-exposing test cases are often available when: (1) developers, at the same time of (or after) submitting bug fixes, create the tests to assure the correctness of the fixes, or (2) regression errors occur. The former case – a scenario commonly used for creating popular bug datasets – however, may not be suitable …

Go to article

Supporting Artefact Awareness In Partially-Replicated Workspaces, Emran Poh, Anthony Tang, Jenanie S. Lee, Zhao Shengdong Oct 2023

Supporting Artefact Awareness In Partially-Replicated Workspaces, Emran Poh, Anthony Tang, Jenanie S. Lee, Zhao Shengdong

Research Collection School Of Computing and Information Systems

Using Cross Reality (CR) approaches for remote collaboration will often result in partially-replicated workspaces. Here, workspace artefacts are not equally accessible - i.e. a physical artefact may only be manipulated by one collaborator - and in general, the artefacts become desynchronised over time. In this paper, we introduce a framework for artefact awareness that can help collaborators maintain an understanding of each others' manipulations with workspace artefacts. We illustrate our design explorations through sketches, and outline how we aim to study the effectiveness and utility of artefact awareness in cross reality remote collaboration. In our work, we expect to show …

Go to article

Achieving Efficient And Privacy-Preserving Neural Network Training And Prediction In Cloud Environments, Chuan Zhang, Chenfei Hu, Tong Wu, Liehuang Zhu, Ximeng Liu Oct 2023

Achieving Efficient And Privacy-Preserving Neural Network Training And Prediction In Cloud Environments, Chuan Zhang, Chenfei Hu, Tong Wu, Liehuang Zhu, Ximeng Liu

Research Collection School Of Computing and Information Systems

The neural network has been widely used to train predictive models for applications such as image processing, disease prediction, and face recognition. To produce more accurate models, powerful third parties (e.g., clouds) are usually employed to collect data from a large number of users, which however may raise concerns about user privacy. In this paper, we propose an Efficient and Privacy-preserving Neural Network scheme, named EPNN, to deal with the privacy issues in cloud-based neural networks. EPNN is designed based on a two-cloud model and techniques of data perturbation and additively homomorphic cryptosystem. This scheme enables two clouds to cooperatively …

Go to article

Icl-D3ie: In-Context Learning With Diverse Demonstrations Updating For Document Information Extraction, Jiabang He, Lei Wang, Yi Hu, Ning Liu, Hui Liu, Xing Xu, Heng Tao Shen Oct 2023

Icl-D3ie: In-Context Learning With Diverse Demonstrations Updating For Document Information Extraction, Jiabang He, Lei Wang, Yi Hu, Ning Liu, Hui Liu, Xing Xu, Heng Tao Shen

Research Collection School Of Computing and Information Systems

arge language models (LLMs), such as GPT-3 and ChatGPT, have demonstrated remarkable results in various natural language processing (NLP) tasks with in-context learning, which involves inference based on a few demonstration examples. Despite their successes in NLP tasks, no investigation has been conducted to assess the ability of LLMs to perform document information extraction (DIE) using in-context learning. Applying LLMs to DIE poses two challenges: the modality and task gap. To this end, we propose a simple but effective in-context learning framework called ICL-D3IE, which enables LLMs to perform DIE with different types of demonstration examples. Specifically, we extract the …

Go to article

Wait, Wasn't That Code Here Before? Detecting Outdated Software Documentation, Wen Siang Tan, Markus Wagner, Christoph Treude Oct 2023

Wait, Wasn't That Code Here Before? Detecting Outdated Software Documentation, Wen Siang Tan, Markus Wagner, Christoph Treude

Research Collection School Of Computing and Information Systems

Encountering outdated documentation is not a rare occurrence for developers and users in the software engineering community. To ensure that software documentation is up-to-date, developers often have to manually check whether the documentation needs to be updated whenever changes are made to the source code. In our previous work, we proposed an approach to automatically detect outdated code element references in software repositories and found that more than a quarter of the 1000 most popular projects on GitHub contained at least one outdated reference. In this paper, we present a GitHub Actions tool that builds on our previous work’s approach …

Go to article

Instance-Specific Algorithm Configuration Via Unsupervised Deep Graph Clustering, Wen Song, Yi Liu, Zhiguang Cao, Yaoxin Wu, Qiqiang Li Oct 2023

Instance-Specific Algorithm Configuration Via Unsupervised Deep Graph Clustering, Wen Song, Yi Liu, Zhiguang Cao, Yaoxin Wu, Qiqiang Li

Research Collection School Of Computing and Information Systems

Instance-specific Algorithm Configuration (AC) methods are effective in automatically generating high-quality algorithm parameters for heterogeneous NP-hard problems from multiple sources. However, existing works rely on manually designed features to describe training instances, which are simple numerical attributes and cannot fully capture structural differences. Targeting at Mixed-Integer Programming (MIP) solvers, this paper proposes a novel instances-specific AC method based on end-to-end deep graph clustering. By representing an MIP instance as a bipartite graph, a random walk algorithm is designed to extract raw features with both numerical and structural information from the instance graph. Then an auto-encoder is designed to learn dense …

Go to article

Robust Bidirectional Poly-Matching, Ween Jiann Lee, Maksim Tkachenko, Hady Wirawan Lauw Oct 2023

Robust Bidirectional Poly-Matching, Ween Jiann Lee, Maksim Tkachenko, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

A fundamental problem in many scenarios is to match entities across two data sources. It is frequently presumed in prior work that entities to be matched are of comparable granularity. In this work, we address one-to-many or poly-matching in the scenario where entities have varying granularity. A distinctive feature of our problem is its bidirectional nature, where the 'one' or the 'many' could come from either source arbitrarily. Moreover, to deal with diverse entity representations that give rise to noisy similarity values, we incorporate novel notions of receptivity and reclusivity into a robust matching objective. As the optimal solution to …

Go to article

Constructing Cyber-Physical System Testing Suites Using Active Sensor Fuzzing, Fan. Zhang, Qianmei. Wu, Bohan. Xuan, Yuqi. Chen, Wei. Lin, Christopher M. Poskitt, Jun Sun, Binbin. Chen Oct 2023

Constructing Cyber-Physical System Testing Suites Using Active Sensor Fuzzing, Fan. Zhang, Qianmei. Wu, Bohan. Xuan, Yuqi. Chen, Wei. Lin, Christopher M. Poskitt, Jun Sun, Binbin. Chen

Research Collection School Of Computing and Information Systems

Cyber-physical systems (CPSs) automating critical public infrastructure face a pervasive threat of attack, motivating research into different types of countermeasures. Assessing the effectiveness of these countermeasures is challenging, however, as benchmarks are difficult to construct manually, existing automated testing solutions often make unrealistic assumptions, and blindly fuzzing is ineffective at finding attacks due to the enormous search spaces and resource requirements. In this work, we propose active sensor fuzzing , a fully automated approach for building test suites without requiring any a prior knowledge about a CPS. Our approach employs active learning techniques. Applied to a real-world water treatment system, …

Go to article

Underwater Image Translation Via Multi-Scale Generative Adversarial Network, Dongmei Yang, Tianzi Zhang, Boquan Li, Menghao Li, Weijing Chen, Xiaoqing Li, Xingmei Wang Oct 2023

Underwater Image Translation Via Multi-Scale Generative Adversarial Network, Dongmei Yang, Tianzi Zhang, Boquan Li, Menghao Li, Weijing Chen, Xiaoqing Li, Xingmei Wang

Research Collection School Of Computing and Information Systems

The role that underwater image translation plays assists in generating rare images for marine applications. However, such translation tasks are still challenging due to data lacking, insufficient feature extraction ability, and the loss of content details. To address these issues, we propose a novel multi-scale image translation model based on style-independent discriminators and attention modules (SID-AM-MSITM), which learns the mapping relationship between two unpaired images for translation. We introduce Convolution Block Attention Modules (CBAM) to the generators and discriminators of SID-AM-MSITM to improve its feature extraction ability. Moreover, we construct style-independent discriminators that enable the discriminant results of SID-AM-MSITM to …

Go to article

Masked Diffusion Transformer Is A Strong Image Synthesizer, Shanghua Gao, Pan Zhou, Ming-Ming Cheng, Shuicheng Yan Oct 2023

Masked Diffusion Transformer Is A Strong Image Synthesizer, Shanghua Gao, Pan Zhou, Ming-Ming Cheng, Shuicheng Yan

Research Collection School Of Computing and Information Systems

Despite its success in image synthesis, we observe that diffusion probabilistic models (DPMs) often lack contextual reasoning ability to learn the relations among object parts in an image, leading to a slow learning process. To solve this issue, we propose a Masked Diffusion Transformer (MDT) that introduces a mask latent modeling scheme to explicitly enhance the DPMs’ ability to contextual relation learning among object semantic parts in an image. During training, MDT operates in the latent space to mask certain tokens. Then, an asymmetric masking diffusion transformer is designed to predict masked tokens from unmasked ones while maintaining the diffusion …

Go to article

Hrgcn: Heterogeneous Graph-Level Anomaly Detection With Hierarchical Relation-Augmented Graph Neural Networks, Jiaxi Li, Guansong Pang, Ling Chen, Mohammad-Reza Namazi-Rad Oct 2023

Hrgcn: Heterogeneous Graph-Level Anomaly Detection With Hierarchical Relation-Augmented Graph Neural Networks, Jiaxi Li, Guansong Pang, Ling Chen, Mohammad-Reza Namazi-Rad

Research Collection School Of Computing and Information Systems

This work considers the problem of heterogeneous graph-level anomaly detection. Heterogeneous graphs are commonly used to represent behaviours between different types of entities in complex industrial systems for capturing as much information about the system operations as possible. Detecting anomalous heterogeneous graphs from a large set of system behaviour graphs is crucial for many real-world applications like online web/mobile service and cloud access control. To address the problem, we propose HRGCN, an unsupervised deep heterogeneous graph neural network, to model complex heterogeneous relations between different entities in the system for effectively identifying these anomalous behaviour graphs. HRGCN trains a hierarchical …

Go to article

Deep Video Demoireing Via Compact Invertible Dyadic Decomposition, Yuhui Quan, Haoran Huang, Shengfeng He, Ruotao Xu Oct 2023

Deep Video Demoireing Via Compact Invertible Dyadic Decomposition, Yuhui Quan, Haoran Huang, Shengfeng He, Ruotao Xu

Research Collection School Of Computing and Information Systems

Removing moire patterns from videos recorded on screens or complex textures is known as video demoireing. It is a challenging task as both structures and textures of an image usually exhibit strong periodic patterns, which thus are easily confused with moire patterns and can be significantly erased in the removal process. By interpreting video demoireing as a multi-frame decomposition problem, we propose a compact invertible dyadic network called CIDNet that progressively decouples latent frames and the moire patterns from an input video sequence. Using a dyadic cross-scale coupling structure with coupling layers tailored for multi-scale processing, CIDNet aims at disentangling …

Go to article

Problems In Microservice Development: Supporting Visualisation, Oscar Manglaras, Alex Farkas, Peter Fule, Christoph Treude, Markus Wagner Oct 2023

Problems In Microservice Development: Supporting Visualisation, Oscar Manglaras, Alex Farkas, Peter Fule, Christoph Treude, Markus Wagner

Research Collection School Of Computing and Information Systems

In microservice architectures, developers can face significant problems understanding the structure of the system and how the different microservices interact. This difficulty results from the distributed nature of the system, and the abundance of inter-service communication within the architecture. We want to determine if network visualisations can address these problems given their ability to convey complex topologies. However, to identify what architectural characteristics should be visualised, and how this should be done, we must first determine the needs of microservice developers. This paper identifies and presents the impact and frequency of problems faced by a cohort of microservice developers using …

Go to article

Voucher Abuse Detection With Prompt-Based Fine-Tuning On Graph Neural Networks, Zhihao Wen, Yuan Fang, Yihan Liu, Yang Guo, Shuji Hao Oct 2023

Voucher Abuse Detection With Prompt-Based Fine-Tuning On Graph Neural Networks, Zhihao Wen, Yuan Fang, Yihan Liu, Yang Guo, Shuji Hao

Research Collection School Of Computing and Information Systems

Voucher abuse detection is an important anomaly detection problem in E-commerce. While many GNN-based solutions have emerged, the supervised paradigm depends on a large quantity of labeled data. A popular alternative is to adopt self-supervised pre-training using label-free data, and further fine-tune on a downstream task with limited labels. Nevertheless, the "pre-train, fine-tune" paradigm is often plagued by the objective gap between pre-training and downstream tasks. Hence, we propose VPGNN, a prompt-based fine-tuning framework on GNNs for voucher abuse detection. We design a novel graph prompting function to reformulate the downstream task into a similar template as the pretext task …

Go to article

Prirpt: Practical Blockchain-Based Privacy-Preserving Reporting System With Rewards, Rui. Shi, Yang Yang, Huamin. Feng, Feng. Yuan, Huiqin. Xie, Jianyi. Zhang Oct 2023

Prirpt: Practical Blockchain-Based Privacy-Preserving Reporting System With Rewards, Rui. Shi, Yang Yang, Huamin. Feng, Feng. Yuan, Huiqin. Xie, Jianyi. Zhang

Research Collection School Of Computing and Information Systems

In order to obtain evidence of a crime timely, most authorities encourage whistleblowers to provide valuable reports by rewarding them with prizes. However, criminals will try their best to delete or tamper with the reports and even threaten and revenge the whistleblowers to escape punishment. Hence, to make the reporting system work, it is essential to ensure the integrity of reported messages and the anonymity of the reporting and rewarding procedures in the reporting system. Most existing schemes for this problem are generally based on ring signatures, which incur high computational overhead and imperfect anonymity. In this paper, we introduce …

Go to article

Experiences Of Autistic Twitch Livestreamers: “I Have Made Easily The Most Meaningful And Impactful Relationships”, Terrance Mok, Anthony Tang, Adam Mccrimmon, Lora Oehlberg Oct 2023

Experiences Of Autistic Twitch Livestreamers: “I Have Made Easily The Most Meaningful And Impactful Relationships”, Terrance Mok, Anthony Tang, Adam Mccrimmon, Lora Oehlberg

Research Collection School Of Computing and Information Systems

We present perspectives from 10 autistic Twitch streamers regarding their experiences as livestreamers and how autism uniquely colors their experiences. Livestreaming offers a social online experience distinct from in-person, face-to-face communication, where autistic people tend to encounter challenges. Our reflexive thematic analysis of interviews with 10 participants showcases autistic livestreamers’ perspectives in their own words. Our findings center on the importance of having streamers establishing connections with other, sharing autistic identities, controlling a space for social interaction, personal growth, and accessibility challenges. In our discussion, we highlight the crucial value of having a medium for autistic representation, as well as …

Go to article

Residual Pattern Learning For Pixel-Wise Out-Of-Distribution Detection In Semantic Segmentation, Y Liu, Choubo Ding, Yu Tian, Guansong Pang, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro Oct 2023

Residual Pattern Learning For Pixel-Wise Out-Of-Distribution Detection In Semantic Segmentation, Y Liu, Choubo Ding, Yu Tian, Guansong Pang, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro

Research Collection School Of Computing and Information Systems

Semantic segmentation models classify pixels into a set of known ("in-distribution") visual classes. When deployed in an open world, the reliability of these models depends on their ability to not only classify in-distribution pixels but also to detect out-of-distribution (OoD) pixels. Historically, the poor OoD detection performance of these models has motivated the design of methods based on model re-training using synthetic training images that include OoD visual objects. Although successful, these re-trained methods have two issues: 1) their in-distribution segmentation accuracy may drop during re-training, and 2) their OoD detection accuracy does not generalise well to new contexts (e.g., …

Go to article

Feature Prediction Diffusion Model For Video Anomaly Detection, Cheng Yan, Shiyu Zhang, Yang Liu, Guansong Pang, Wenjun Wang Oct 2023

Feature Prediction Diffusion Model For Video Anomaly Detection, Cheng Yan, Shiyu Zhang, Yang Liu, Guansong Pang, Wenjun Wang

Research Collection School Of Computing and Information Systems

Anomaly detection in the video is an important research area and a challenging task in real applications. Due to the unavailability of large-scale annotated anomaly events, most existing video anomaly detection (VAD) methods focus on learning the distribution of normal samples to detect the substantially deviated samples as anomalies. To well learn the distribution of normal motion and appearance, many auxiliary networks are employed to extract foreground object or action information. These high-level semantic features effectively filter the noise from the background to decrease its influence on detection models. However, the capability of these extra semantic models heavily affects the …

Go to article

Owner-Free Distributed Symmetric Searchable Encryption Supporting Conjunctive Queries, Qiuyun Tong, Xinghua Li, Yinbin Miao, Yunwei Wang, Ximeng Liu, Robert H. Deng Oct 2023

Owner-Free Distributed Symmetric Searchable Encryption Supporting Conjunctive Queries, Qiuyun Tong, Xinghua Li, Yinbin Miao, Yunwei Wang, Ximeng Liu, Robert H. Deng

Research Collection School Of Computing and Information Systems

Symmetric Searchable Encryption (SSE), as an ideal primitive, can ensure data privacy while supporting retrieval over encrypted data. However, existing multi-user SSE schemes require the data owner to share the secret key with all query users or always be online to generate search tokens. While there are some solutions to this problem, they have at least one weakness, such as non-supporting conjunctive query, result decryption assistance of the data owner, and unauthorized access. To solve the above issues, we propose an Owner-free Distributed Symmetric searchable encryption supporting Conjunctive query (ODiSC). Specifically, we first evaluate the Learning-Parity-with-Noise weak Pseudorandom Function (LPN-wPRF) …

Go to article

Diffuse3d: Wide-Angle 3d Photography Via Bilateral Diffusion, Yutao Jiang, Yang Zhou, Yuan Liang, Wenxi Liu, Jianbo Jiao, Yuhui Quan, Shengfeng He Oct 2023

Diffuse3d: Wide-Angle 3d Photography Via Bilateral Diffusion, Yutao Jiang, Yang Zhou, Yuan Liang, Wenxi Liu, Jianbo Jiao, Yuhui Quan, Shengfeng He

Research Collection School Of Computing and Information Systems

This paper aims to resolve the challenging problem of wide-angle novel view synthesis from a single image, a.k.a. wide-angle 3D photography. Existing approaches rely on local context and treat them equally to inpaint occluded RGB and depth regions, which fail to deal with large-region occlusion (i.e., observing from an extreme angle) and foreground layers might blend into background inpainting. To address the above issues, we propose Diffuse3D which employs a pre-trained diffusion model for global synthesis, while amending the model to activate depth-aware inference. Our key insight is to alter the convolution mechanism in the denoising process. We inject depth …

Go to article

Learning Provably Stabilizing Neural Controllers For Discrete-Time Stochastic Systems, Matin Ansaripour, Krishnendu Chatterjee, A. Thomas Henzinger, Mathias Lechner, Dorde Zikelic Oct 2023

Learning Provably Stabilizing Neural Controllers For Discrete-Time Stochastic Systems, Matin Ansaripour, Krishnendu Chatterjee, A. Thomas Henzinger, Mathias Lechner, Dorde Zikelic

Research Collection School Of Computing and Information Systems

We consider the problem of learning control policies in discrete-time stochastic systems which guarantee that the system stabilizes within some specified stabilization region with probability 1. Our approach is based on the novel notion of stabilizing ranking supermartingales (sRSMs) that we introduce in this work. Our sRSMs overcome the limitation of methods proposed in previous works whose applicability is restricted to systems in which the stabilizing region cannot be left once entered under any control policy. We present a learning procedure that learns a control policy together with an sRSM that formally certifies probability 1 stability, both learned as neural …

Go to article

Visilience: An Interactive Visualization Framework For Resilience Analysis Using Control-Flow Graph, Hailong Jiang, Shaolun Ruan, Bo Fang, Yong Wang, Qiang Guan Oct 2023

Visilience: An Interactive Visualization Framework For Resilience Analysis Using Control-Flow Graph, Hailong Jiang, Shaolun Ruan, Bo Fang, Yong Wang, Qiang Guan

Research Collection School Of Computing and Information Systems

Soft errors have become one of the main concerns for the resilience of HPC applications, as these errors can cause HPC applications to generate serious outcomes such as silent data corruption (SDC). Many approaches have been proposed to analyze the resilience of HPC applications. However, existing studies rarely address the challenges of analysis result perception. Specifically, resilience analysis techniques often produce a massive volume of unstructured data, making it difficult for programmers to perform resilience analysis due to non-intuitive raw data. Furthermore, different analysis models produce diverse results with multiple levels of detail, which can create obstacles to compare and …

Go to article

Towards An Effective And Interpretable Refinement Approach For Dnn Verification, Jiaying Li, Guangdong Bai, Long H. Pham, Jun Sun Oct 2023

Towards An Effective And Interpretable Refinement Approach For Dnn Verification, Jiaying Li, Guangdong Bai, Long H. Pham, Jun Sun

Research Collection School Of Computing and Information Systems

Recently, several abstraction refinement techniques have been proposed to improve the verification precision for deep neural networks (DNNs). However, these techniques usually take many refinement steps to verify a property and the refinement decision in each step is hard to interpret, thus hindering their analysis, reasoning and optimization.In this work, we propose SURGEON, a novel DNN verification refinement approach that is both effective and interpretable, allowing analyst to understand why and how each refinement decision is made. The main insight is to leverage the ‘interpretable’ nature of debugging processes and formulate the verification refinement problem as a debugging problem. Given …

Go to article

Visually Analyzing Company-Wide Software Service Dependencies: An Industrial Case Study, Sebastian Baltes, Brian Pfitzmann, Thomas Kowark, Christoph Treude, Fabian Beck Oct 2023

Visually Analyzing Company-Wide Software Service Dependencies: An Industrial Case Study, Sebastian Baltes, Brian Pfitzmann, Thomas Kowark, Christoph Treude, Fabian Beck

Research Collection School Of Computing and Information Systems

Managing dependencies between software services is a crucial task for any company operating cloud applications. Visualizations can help to understand and maintain these com-plex dependencies. In this paper, we present a force-directed service dependency visualization and filtering tool that has been developed and used within SAP. The tool's use cases include guiding service retirement as well as understanding service deployment landscapes and their relationship to the company's organizational structure. We report how we built and adapted the tool under strict time constraints to address the requirements of our users. We further share insights on how we enabled internal adoption. For …

Go to article

First Prev Next Last