Introduction of Explicit Visual Saliency in Training of Deep CNNs: Application to Architectural Styles Classification

Obeso, Abraham Montoya; Benois-Pineau, Jenny; Vázquez, Mireya Saraí García; Acosta, Alejandro

doi:10.1109/cbmi.2018.8516465

Cited by 6 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This uses both existing and custom-made image recognition models. The primary objective of this research is to improve process expediency [76], optimise processing tasks, or enhance accuracy [18,48]. Once automated, the virtual scene understanding is then deployed in space navigation and virtual visual servoing [96].…”

Section: Research Trendsmentioning

confidence: 99%

Computer Vision-based Analysis of Buildings and Built Environments: A Systematic Review of Current Approaches

et al. 2023

View full text Add to dashboard Cite

Analysing 88 sources published from 2011 to 2021, this paper presents a first systematic review of the computer vision-based analysis of buildings and the built environment. Its aim is to assess the potential of this research for architectural studies and the implications of a shift to a crossdisciplinarity approach between architecture and computer science for research problems, aims, processes, and applications. To this end, the types of algorithms and data sources used in the reviewed studies are discussed in respect to architectural applications such as a building classification, detail classification, qualitative environmental analysis, building condition survey, and building value estimation. Based on this, current research gaps and trends are identified, with two main research aims emerging. First, studies that use or optimise computer vision methods to automate time-consuming, labour-intensive, or complex tasks when analysing architectural image data. Second, work that explores the methodological benefits of machine learning approaches to overcome limitations of conventional analysis in order to investigate new questions about the built environment by finding patterns and relationships between visual, statistical, and qualitative data. The growing body of research offers new methods to architectural and design studies, with the paper identifying future challenges and directions of research.

show abstract

Section: Research Trendsmentioning

confidence: 99%

Computer Vision-based Analysis of Buildings and Built Environments: A Systematic Review of Current Approaches

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In the context of incremental learning, we are receiving new data (x T , y T ) on the fly. For each new data point we apply the formula (7). This procedure we call Move-to-Data.…”

Section: "Move-to-data": Incremental Learning Approach For a Deep Cnnmentioning

confidence: 99%

“…The motivation of it was the recognition of objects to grasp in assistance to amputees with vision-based Neuro-prostheses [16], [17] when different views of the same object -to-grasp come "on the fly" to adjust the pre-trained model. Another scenario is continual image database enrichment as in the application of [7]. We show that the method performs "not worse" than continual learning by sequential gradient descent optimization.…”

Section: Introduction and Related Workmentioning

confidence: 97%

“…incremental clustering [3], [4], [5]. In supervised (Deep Neural Networks) framework, while offline models have shown to be successful in an abundance of fields, such as medical image classification [6], recognition of historical objects in digital cultural heritage management [7] and others, online models still seem to lack effectiveness. The scenarios which might require continual learning approaches are the following but not limited to: i) introduction of new categories from new coming data [8], specifically with a few data [9]; ii) refining existing categories to sub categories (hierarchical classification) [10]; iii) additional training data for existing categories.…”

Section: Introduction and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Move-to-Data: A new Continual Learning approach with Deep CNNs, Application for image-class recognition

Poursanidis,

Benois-Pineau,

Zemmari

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

In many real-life tasks of application of supervised learning approaches, all the training data are not available at the same time. The examples are life-long image classification or recognition of environmental objects during interaction of instrumented persons with their environment, enrichment of an online-database with more images. It is necessary to pre-train the model at a "training recording phase" and then adjust it to the new coming data. This is the task of incremental/continual learning approaches. Amongst different problems to be solved by these approaches such as introduction of new categories in the model, refining existing categories to sub-categories and extending trained classifiers over them, ... we focus on the problem of adjusting pre-trained model with new additional training data for existing categories. We propose a fast continual learning layer at the end of the neuronal network. Obtained results are illustrated on the opensource CIFAR benchmark dataset. The proposed scheme yields similar performances as retraining but with drastically lower computational cost.

show abstract

Deep multiple aggregation networks for action recognition

Mazari,

Sahbi

2024

Int J Multimed Info Retr

View full text Add to dashboard Cite

Introduction of Explicit Visual Saliency in Training of Deep CNNs: Application to Architectural Styles Classification

Cited by 6 publications

References 10 publications

Computer Vision-based Analysis of Buildings and Built Environments: A Systematic Review of Current Approaches

Computer Vision-based Analysis of Buildings and Built Environments: A Systematic Review of Current Approaches

Move-to-Data: A new Continual Learning approach with Deep CNNs, Application for image-class recognition

Deep multiple aggregation networks for action recognition

Contact Info

Product

Resources

About