Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks

Shaheen, Khadija; Hanif, Muhammad Abdullah; Hasan, Osman; Shafique, Muhammad

doi:10.48550/arxiv.2105.12374

Cited by 3 publications

(7 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Regularization-based Approach: This method consolidates past knowledge by incorporating additional loss terms that reduce the rate of learning for important weights used in previously learned tasks. By doing so, it minimizes the risk of new task information significantly altering the previously acquired weights (Shaheen et al, 2022). An example of this approach is Elastic Weight Consolidation (EWC), which penalizes weight changes based on task importance, regularizing model parameters and preventing catastrophic forgetting of previous experiences (Febrinanto et al, 2022).…”

Section: Lifelong Learningmentioning

confidence: 99%

Advancing autonomy through lifelong learning: a survey of autonomous intelligent systems

Zhu,

Bu,

Zhu

et al. 2024

Front. Neurorobot.

View full text Add to dashboard Cite

The combination of lifelong learning algorithms with autonomous intelligent systems (AIS) is gaining popularity due to its ability to enhance AIS performance, but the existing summaries in related fields are insufficient. Therefore, it is necessary to systematically analyze the research on lifelong learning algorithms with autonomous intelligent systems, aiming to gain a better understanding of the current progress in this field. This paper presents a thorough review and analysis of the relevant work on the integration of lifelong learning algorithms and autonomous intelligent systems. Specifically, we investigate the diverse applications of lifelong learning algorithms in AIS’s domains such as autonomous driving, anomaly detection, robots, and emergency management, while assessing their impact on enhancing AIS performance and reliability. The challenging problems encountered in lifelong learning for AIS are summarized based on a profound understanding in literature review. The advanced and innovative development of lifelong learning algorithms for autonomous intelligent systems are discussed for offering valuable insights and guidance to researchers in this rapidly evolving field.

show abstract

Section: Lifelong Learningmentioning

confidence: 99%

Advancing autonomy through lifelong learning: a survey of autonomous intelligent systems

Zhu,

Bu,

Zhu

et al. 2024

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…Shin et al [35] proposed to train a generative model on the old data distribution and use it to generate fake samples that help in mitigating the forgetting of old classes. Although having the downside of the model's performance being upper-bounded by the joint-training in all tasks [20], the replay family has been the most consistently used strategy in real-world applications of CL [6,36].…”

Section: Parameter Isolation Techniquesmentioning

confidence: 99%

“…Contrastively, the CIOD paradigm needs a more specific treatment due to its inherent challenges and complexity. The task of incrementally adding classes to a trained detector is considered of substantial importance for several applications that deal with memory and computational constraints [6]. The main issue that makes detection a more difficult task than only classification for class-incremental scenarios is that the same image can have several instances of different objects that are unknown apriori.…”

Section: Continual Learning For Object Detectionmentioning

confidence: 99%

“…Within the context of computer vision, the search for strategies able to deal with the modeling of a dynamic world is not new [5]. Several applications associated with streams of images can benefit from having models able to naturally work with changing and incremental contexts, such as autonomous Email address: angelomenezes@usp.br (Angelo G. Menezes) cars, Unmanned Aerial Vehicles and house robots [6]. Notwithstanding, most of the current solutions for CL consider the classification task as its main conundrum.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Continual Object Detection: A review of definitions, strategies, and challenges

Menezes¹,

Moura²,

Alves³

et al. 2022

Preprint

View full text Add to dashboard Cite

The field of Continual Learning investigates the ability to learn consecutive tasks without losing performance on those previously learned. Its focus has been mainly on incremental classification tasks. We believe that research in continual object detection deserves even more attention due to its vast range of applications in robotics and autonomous vehicles. This scenario is more complex than conventional classification given the occurrence of instances of classes that are unknown at the time, but can appear in subsequent tasks as a new class to be learned, resulting in missing annotations and conflicts with the background label. In this review, we analyze the current strategies proposed to tackle the problem of class-incremental object detection. Our main contributions are:(1) a short and systematic review of the methods that propose solutions to traditional incremental object detection scenarios; (2) A comprehensive evaluation of the existing approaches using a new metric to quantify the stability and plasticity of each technique in a standard way; (3) an overview of the current trends within continual object detection and a discussion of possible future research directions.

show abstract

“…Several applications that deal with streams of images can benefit from having models that can naturally deal with changing and incremental contexts, such as autonomous cars, UAVs, and house robots (SHAHEEN et al, 2021). Applications of CL for object detection are the main focus of this Ph.D., which will be discussed more deeply in the following sections.…”

Section: Phd Thesis Contextmentioning

confidence: 99%

Continual Object Detection with Deep Neural Networks

Menezes

View full text Add to dashboard Cite

The rapid technological development in the past decades has significantly increased the amount of available data in the world. Naturally, models that scale with the size of the available data, such as Deep Neural Networks, have become the primary strategy for several research fields with abundant data (e.g., computer vision and natural language processing). With this large data availability, research on learning models that can adapt incrementally to continual streams of data has been encouraged. In this way, the field of Continual Learning proposes to study the ability to learn consecutive tasks without losing performance on the previously trained ones. In computer vision, researchers have mainly focused their efforts on incremental classification tasks, but continual object detection also deserves attention due to its vast range of applications in robotics and autonomous vehicles. In fact, this scenario is even more complex than conventional classification, given the occurrence of instances of classes that are unknown at the time but can appear in subsequent tasks as a new class to be learned, resulting in missing annotations and conflicts with the background label. Since this field is in its early stages, research in continual object detection still offers several opportunities and lacks methodology conventions. This Ph.D. thesis investigates the field more thoroughly and identifies possible links with related areas such as general continual learning and neural network pruning. Specifically, we proposed the first systematic review on the topic, developed two metrics for improving the analysis of performance in incremental detection scenarios, investigated which exemplar selection method works best for replay-based continual detection strategies, and explored different ways to identify and penalize important task parameters across sequential updates. To validate our proposals and claims, we conducted experiments and reported results comparable to the current state-of-the-art in popular detection benchmarks (i.e., PASCAL VOC) adapted to the incremental setting, as well as in real-world datasets and applications. The findings presented in this thesis were also put into practice in two applications. Firstly, they were tested in the 3 rd CLVISION Challenge, where we were able to achieve the 3 rd place in the continual instance detection track. Secondly, they were applied to the continual aerial inspection of transmission towers at TAESA, the largest Brazilian electric power transmission company, to improve the automation of their inspection pipeline.

show abstract

Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks

Cited by 3 publications

References 62 publications

Advancing autonomy through lifelong learning: a survey of autonomous intelligent systems

Advancing autonomy through lifelong learning: a survey of autonomous intelligent systems

Continual Object Detection: A review of definitions, strategies, and challenges

Continual Object Detection with Deep Neural Networks

Contact Info

Product

Resources

About