相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Review
Computer Science, Theory & Methods
Dana Pessach et al.
Summary: This article discusses the issue of fairness in ML algorithms, highlighting the potential unfairness in algorithmic decision making and proposing mechanisms to enhance fairness. The article also reviews emerging research areas in algorithmic fairness and emphasizes that fairness issues extend beyond classification tasks.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Software Engineering
Mahsan Nourani et al.
Summary: This article proposes DETOXER, an interactive visual debugging system, to support finding different error types and scopes in video activity recognition.
IEEE COMPUTER GRAPHICS AND APPLICATIONS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Rocio Nahime Torres et al.
Summary: This article introduces an open-source diagnosis framework called ODIN for generic machine learning classification tasks and computer vision object detection and instance segmentation tasks. The framework allows developers to add meta-annotations to their datasets, compute performance metrics based on meta-annotation values, and visualize diagnosis reports. ODIN is platform and input format agnostic and can be easily extended with application- and domain-specific meta-annotations and metrics.
MACHINE LEARNING, OPTIMIZATION, AND DATA SCIENCE (LOD 2021), PT I
(2022)
Review
Physics, Multidisciplinary
Pantelis Linardatos et al.
Summary: Recent advances in artificial intelligence have led to widespread industrial adoption, with machine learning systems demonstrating superhuman performance. However, the complexity of these systems has made them difficult to explain, hindering their application in sensitive domains. Therefore, there is a renewed interest in the field of explainable artificial intelligence.
Article
Computer Science, Information Systems
Rafael Padilla et al.
Summary: This study provides an overview of evaluation methods used in object detection competitions, examines the influence of different annotation formats on evaluation results, and offers an open-source toolkit supporting various annotation formats and performance metrics for researchers to evaluate their detection algorithms. Furthermore, it introduces a new metric for evaluating object detection in videos based on spatio-temporal overlap.
Review
Computer Science, Theory & Methods
Guansong Pang et al.
Summary: Deep anomaly detection has emerged as a critical direction in the research field of anomaly detection, covering advancements in multiple categories of methods. Reviewing them can help us understand their advantages, disadvantages, and how they address challenges.
ACM COMPUTING SURVEYS
(2021)
Article
Computer Science, Theory & Methods
El-Ghazali Talbi
Summary: This article proposes a unified way to describe various optimization algorithms, focusing on common and important search components. This methodology has also been extended to advanced optimization approaches including surrogate-based, multi-objective, and parallel optimization.
ACM COMPUTING SURVEYS
(2021)
Article
Computer Science, Software Engineering
Gharib Gharibi et al.
Summary: Deep learning has improved state-of-the-art results in many domains, but the management of models and their artifacts remains a challenging and time-consuming process.
ModelKB is a software system that can automatically manage the various stages of the deep learning modeling lifecycle, including monitoring experiments, deploying models, and sharing trained models.
EMPIRICAL SOFTWARE ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Jacinto Carrasco et al.
Summary: The research in anomaly detection lacks a unified definition of what represents an anomalous instance, leading to diverse paradigms in algorithm design and experimentation. Predictive maintenance represents a special case, where anomalies must be prevented to avoid failures. To address these issues, the concept of positive and negative instances has been generalized into intervals for evaluating unsupervised anomaly detection algorithms.
Article
Computer Science, Artificial Intelligence
Erico Tjoa et al.
Summary: Artificial intelligence and machine learning have shown remarkable performances in various fields, but the challenge of interpretability remains. The medical sector requires higher levels of interpretability to ensure the reliability of machine decisions, and a deeper understanding of the mechanisms behind machine algorithms is needed to advance medical practices.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Humanities, Multidisciplinary
Federico Milani et al.
Summary: Iconography in art is a discipline that studies the visual content of artworks using techniques like Convolutional Neural Networks to support research and education. By quantitatively and qualitatively analyzing the iconography of saints in Christian religious paintings, it is found that CNN focuses on traditional motifs for successful identification.
ACM JOURNAL ON COMPUTING AND CULTURAL HERITAGE
(2021)
Article
Chemistry, Multidisciplinary
Martin Kraeter et al.
Summary: AID is an easy-to-use, adaptable, and open source software for training neural networks for image classification without the need for programming. It allows for a variety of neural network architectures, benchmarking on large image datasets, and interdisciplinary use by non-programmers on generic computers.
Article
Computer Science, Theory & Methods
Ninareh Mehrabi et al.
Summary: With the widespread use of AI systems in everyday life, fairness in design has become crucial. Researchers have developed methods to address biases in different subdomains and established a taxonomy for fairness definitions. Existing work shows biases in AI applications, and researchers are working on solutions to mitigate these problems.
ACM COMPUTING SURVEYS
(2021)
Proceedings Paper
Automation & Control Systems
Simon Vollert et al.
Summary: With the increasing importance of machine learning in the field of predictive maintenance, more research is focusing on the interpretability of models. This paper reviews publications addressing PdM problems motivated by model interpretability and identifies challenges for interpretable ML.
2021 26TH IEEE INTERNATIONAL CONFERENCE ON EMERGING TECHNOLOGIES AND FACTORY AUTOMATION (ETFA)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Agathe Balayn et al.
Summary: This paper introduces a scalable human-in-the-loop approach for global interpretability in image classification, which annotates salient image areas identified by local interpretability methods with semantic concepts and aggregates them into a tabular representation for automatic statistical analysis. This approach addresses the interpretability needs for model validation and exploration, providing diverse, informative, and relevant explanations while still being scalable and cost-efficient.
PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE 2021 (WWW 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Vitali Petsiuk et al.
Summary: D-RISE is a method for generating visual explanations for object detector predictions, utilizing a proposed similarity metric to produce saliency maps showing image areas that most affect the prediction. It is considered black-box in software testing, being more general than gradient-based methods and agnostic to the type of object detector.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Information Systems
Vito Walter Anelli et al.
Summary: Recommender Systems have been effective in providing tailored recommendations, but the variety of algorithms, strategies, and evaluation methods makes rigorous experimental evaluation challenging. The Elliot framework aims to address these challenges by running and reproducing entire experimental pipelines with a simple configuration file, including data processing, hyperparameter optimization, model selection, metric computation, and statistical analysis.
SIGIR '21 - PROCEEDINGS OF THE 44TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Heng Fan et al.
Summary: The paper introduces a tracking diagnosis toolkit, TracKlinic, for diagnosing challenge factors of tracking algorithms, consisting of two novel components focusing on data and analysis aspects. A thorough study is conducted on ten state-of-the-art trackers on nine challenge factors, revealing that shape variation and occlusion are the most challenging factors faced by most trackers.
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021)
(2021)
Article
Computer Science, Information Systems
Ilia Stepin et al.
Summary: This study presents a systematic literature review on contrastive and counterfactual explanations in artificial intelligence algorithms, examining theoretical foundations and computational frameworks. The research reveals shortcomings in existing approaches and proposes a taxonomy for theoretical and practical methods in contrastive and counterfactual explanation.
Article
Computer Science, Software Engineering
Michael Gleicher et al.
COMPUTER GRAPHICS FORUM
(2020)
Article
Computer Science, Information Systems
Kyung Ho Sun et al.
Article
Computer Science, Information Systems
Ribana Roscher et al.
Article
Computer Science, Theory & Methods
Riccardo Guidotti et al.
ACM COMPUTING SURVEYS
(2019)
Article
Computer Science, Software Engineering
Jiawei Zhang et al.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2019)
Article
Engineering, Multidisciplinary
Zhaobin Wang et al.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2019)
Review
Computer Science, Information Systems
Diogo Carvalho et al.
Article
Computer Science, Information Systems
Weiting Zhang et al.
IEEE SYSTEMS JOURNAL
(2019)
Article
Computer Science, Information Systems
Haruna Chiroma et al.
Proceedings Paper
Computer Science, Software Engineering
Tommaso Zoppi et al.
2019 IEEE 30TH INTERNATIONAL SYMPOSIUM ON SOFTWARE RELIABILITY ENGINEERING (ISSRE)
(2019)
Proceedings Paper
Computer Science, Software Engineering
Xindi Shang et al.
ICMR'19: PROCEEDINGS OF THE 2019 ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL
(2019)
Article
Engineering, Electrical & Electronic
Gregoire Montavon et al.
DIGITAL SIGNAL PROCESSING
(2018)
Article
Computer Science, Software Engineering
Jaegul Choo et al.
IEEE COMPUTER GRAPHICS AND APPLICATIONS
(2018)
Article
Geography, Physical
Zhipeng Deng et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2018)
Review
Mathematical & Computational Biology
Athanasios Voulodimos et al.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2018)
Review
Computer Science, Information Systems
Quan-shi Zhang et al.
FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING
(2018)
Article
Computer Science, Software Engineering
Donghao Ren et al.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2017)
Article
Computer Science, Artificial Intelligence
Weibo Liu et al.
Proceedings Paper
Computer Science, Cybernetics
Saleema Amershi et al.
CHI 2015: PROCEEDINGS OF THE 33RD ANNUAL CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS
(2015)
Article
Biochemistry & Molecular Biology
Matthew E. Falagas et al.
