Local-LDA: Open-Ended Learning of Latent Topics for 3D Object Recognition

Kasaei, S. Hamidreza; Lopes, Luís Seabra; Tomé, Ana Maria

doi:10.1109/tpami.2019.2926459

Cited by 13 publications

(41 citation statements)

References 48 publications

(66 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, a simulated teacher has been developed to interact with the model and evaluate its performance in an open-ended manner. This work extends two approaches, namely Local-LDA [8] and HDP [11], in four aspects. First, our approach can autonomously detect the number of required topics to independently represent the objects in each category, avoiding the limitation of Local-LDA for determining the number of topics in advance.…”

Section: Introductionmentioning

confidence: 91%

“…Therefore, the model should get updated in an open-ended manner without completely retraining the model [7]. Furthermore, object category recognition is not a well-defined problem because of the large intra-category variation (Figure 1 (a)), multiple object views for each object (Figure 1 (b)), and concept drift in dynamic environments [8].…”

Section: Introductionmentioning

confidence: 99%

“…We propose the Local Hierarchical Dirichlet Process (Local-HDP), an extension of the Hierarchical Dirichlet Process [11] method, which can incrementally learn new topics for each category of objects independently. In contrast to the notable recent works [8,12,13] using a predefined number of topics, Local-HDP is more flexible since it is a non-parametric Bayesian model that can autonomously determine the number of topics for each category at run-time. Figure 2 shows the processing layers of the proposed Local-HDP.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Local-HDP: Interactive Open-Ended 3D Object Categorization in Real-Time Robotic Scenarios

Ayoobi,

Kasaei,

Cao

et al. 2020

Preprint

View full text Add to dashboard Cite

We introduce a non-parametric hierarchical Bayesian approach for open-ended 3D object categorization, named the Local Hierarchical Dirichlet Process (Local-HDP). This method allows an agent to learn independent topics for each category incrementally and to adapt to the environment in time. Hierarchical Bayesian approaches like Latent Dirichlet Allocation (LDA) can transform low-level features to high-level conceptual topics for 3D object categorization. However, the efficiency and accuracy of LDA-based approaches depend on the number of topics that is chosen manually. Moreover, fixing the number of topics for all categories can lead to overfitting or underfitting of the model. In contrast, the proposed Local-HDP can autonomously determine the number of topics for each category. Furthermore, an inference method is proposed that results in a fast posterior approximation. Experiments show that Local-HDP outperforms other state-of-the-art approaches in terms of accuracy, scalability, and memory efficiency with a large margin.

show abstract

Section: Introductionmentioning

confidence: 91%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Local-HDP: Interactive Open-Ended 3D Object Categorization in Real-Time Robotic Scenarios

Ayoobi,

Kasaei,

Cao

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Additional training and recognition on new objects and categories is approached in a number of different ways, some use few-shot learning [52,59,148,192], others use one-class support vector machines [105] and random forests [165], and simple instance-based learning is also combined with nearest neighbor classification [59,84,193]. Other learning approaches have also been considered, such as the use of autoencoder-based representation learning [191,219], Bag of Words [86,88,145], and topic modeling [89,92,94]. To accommodate the significant computational power some of these methods need, some have proposed the use of cloud services to replace costly on-board hardware [12,142].…”

Section: Object Category Learning and Recognitionmentioning

confidence: 99%

“…Several types of research have been performed to assess the added-value of structural information. Kasaei et al [94] proposed an open-ended object category learning approach just by learning specific topics per category. In another work [83], an approach is proposed to learn a set of general topics for basic-level categorization, and a category-specific dictionary for fine-grained categorization (Fig.…”

Section: Fine-grained Object Recognitionmentioning

confidence: 99%

The State of Lifelong Learning in Service Robots:

Kasaei

Melsen

Beers

et al. 2021

J Intell Robot Syst

Self Cite

View full text Add to dashboard Cite

Service robots are appearing more and more in our daily life. The development of service robots combines multiple fields of research, from object perception to object manipulation. The state-of-the-art continues to improve to make a proper coupling between object perception and manipulation. This coupling is necessary for service robots not only to perform various tasks in a reasonable amount of time but also to continually adapt to new environments and safely interact with non-expert human users. Nowadays, robots are able to recognize various objects, and quickly plan a collision-free trajectory to grasp a target object in predefined settings. Besides, in most of the cases, there is a reliance on large amounts of training data. Therefore, the knowledge of such robots is fixed after the training phase, and any changes in the environment require complicated, time-consuming, and expensive robot re-programming by human experts. Therefore, these approaches are still too rigid for real-life applications in unstructured environments, where a significant portion of the environment is unknown and cannot be directly sensed or controlled. In such environments, no matter how extensive the training data used for batch learning, a robot will always face new objects. Therefore, apart from batch learning, the robot should be able to continually learn about new object categories and grasp affordances from very few training examples on-site. Moreover, apart from robot self-learning, non-expert users could interactively guide the process of experience acquisition by teaching new concepts, or by correcting insufficient or erroneous concepts. In this way, the robot will constantly learn how to help humans in everyday tasks by gaining more and more experiences without the need for re-programming. In this paper, we review a set of previously published works and discuss advances in service robots from object perception to complex object manipulation and shed light on the current challenges and bottlenecks.

show abstract

AI Autonomy: Self‐initiated Open‐world Continual Learning and Adaptation

Liu

Mazumder

Robertson³

et al. 2023

AI Magazine

View full text Add to dashboard Cite

As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can (1) learn by themselves continually in a self-motivated and self-initiated manner rather than being retrained offline periodically on the initiation of human engineers and (2) accommodate or adapt to unexpected or novel circumstances. As the real-world is an open environment that is full of unknowns or novelties, the capabilities of detecting novelties, characterizing them, accommodating/adapting to them, and gathering ground-truth training data and incrementally learning the unknowns/novelties become critical in making the AI agent more and more knowledgeable, powerful and self-sustainable over time. The key challenge here is how to automate the process so that it is carried out continually on the agent's own initiative and through its own interactions with humans, other agents and the environment just like human on-the-job learning. This paper proposes a framework (called SOLA) for this learning paradigm to promote the research of building autonomous and continual learning enabled AI agents. To show feasibility, an implemented agent is also described.

show abstract

Local-LDA: Open-Ended Learning of Latent Topics for 3D Object Recognition

Cited by 13 publications

References 48 publications

Local-HDP: Interactive Open-Ended 3D Object Categorization in Real-Time Robotic Scenarios

Local-HDP: Interactive Open-Ended 3D Object Categorization in Real-Time Robotic Scenarios

The State of Lifelong Learning in Service Robots:

AI Autonomy: Self‐initiated Open‐world Continual Learning and Adaptation

Contact Info

Product

Resources

About