Deep Transfer Learning for Art Classification Problems

Sabatelli, Matthia; Kestemont, Mike; Daelemans, Walter; Geurts, Pierre

doi:10.1007/978-3-030-11012-3_48

Cited by 45 publications

(47 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inductive TL [ 18 ] is the branch of TL related to problems where we have datasets of input-output pairs in both source and target domains, and where and . Typically, inductive TL is used to repurpose well known, efficient machine learning models trained on large datasets to related problems with smaller training datasets [ 19 , 21 ].…”

Section: Transfer Learning For Water Segmentationmentioning

confidence: 99%

Automated Water Segmentation and River Level Detection on Camera Images Using Transfer Learning

Vandaele

Dance

Ojha

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We investigate a deep transfer learning methodology to perform water segmentation and water level prediction on river camera images. Starting from pre-trained segmentation networks that provided state-of-the-art results on general purpose semantic image segmentation datasets ADE20k and COCO-stuff, we show that we can apply transfer learning methods for semantic water segmentation. Our transfer learning approach improves the current segmentation results of two water segmentation datasets available in the literature. We also investigate the usage of the water segmentation networks in combination with on-site ground surveys to automate the process of water level estimation on river camera images. Our methodology has the potential to impact the study and modelling of flood-related events.

show abstract

Section: Transfer Learning For Water Segmentationmentioning

confidence: 99%

Automated Water Segmentation and River Level Detection on Camera Images Using Transfer Learning

Vandaele

Dance

Ojha

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The evaluation based on transfer learning mainly refers to the transfer of natural image related algorithms and knowledge into the aesthetic assessment of artistic images. Sabatelli et al [92] used the VisualBackProp visualization method [93] to observe the deep neural network before and after fine-tuning weights, which shows that the network activation area before fine-tuning is mainly concentrated in the location indicated the object type, and the active area is then moved into the position that is more related to the specific task in art paintings after fine-tuning. Li et al [78] applied deep convolutional features in the classification and evaluation of sketch copy works, which were collected in the teaching scenario including 25 types of works (such as apple, ceramic pot, glass, cube, molectron, etc.…”

Section: A Multi-task Probabilistic Frameworkmentioning

confidence: 99%

A Comprehensive Survey on Computational Aesthetic Evaluation of Visual Art Images: Metrics and Challenges

Zhang

Miao

2021

IEEE Access

View full text Add to dashboard Cite

Computational image aesthetic evaluation is a computable human aesthetic perception and judgment realized by machines, which has a significant impact on a variety of applications such as image advanced search and promotional exhibition of painting arts. Various approaches have been proposed in copious literature trying to solve this challenging problem. However, there have been few attempts in reviewing works from different types of visual arts, due to their significant differences in visual features and aesthetic principles. In this survey, we present a comprehensive listing of the reviewed works on aesthetic assessment of photographs and paintings, mainly highlighting the contributions and innovations of the existing approaches. We firstly introduce aesthetic assessment benchmark datasets in different categories. Then, conventional aesthetic evaluation approaches based on handcrafted features are reviewed. Besides, we systematically evaluate recent deep learning techniques that are useful for developing robust models for aesthetic prediction tasks in scoring, distribution, attribute, and description. Moreover, the possibility of aesthetic-aware color enhancement, recomposition of photo images, and automatic generation of aestheticguided art paintings through computational approaches are summarized. Finally, challenges and potential future directions for this field are discussed. We hope that our survey could serve as a comprehensive reference source for future research on computational aesthetics in visual media.

show abstract

“…networks are trained on small datasets composed of 100-300 training images (Lopez-Fuentes et al, 2017;Steccanella et al, 2018;Moy de Vitry et al, 2019) while more popular problems can be trained on datasets composed of more than 15000 images (e.g, Caesar et al (2018); Zhou et al (2017)). In many cases, using inductive TL approaches for the training of CNNs instead of training them from scratch, with randomly initialised weights, allows improvement in the network performance (Reyes et al, 2015;Sabatelli et al, 2018).…”

Section: Transfer Learningmentioning

confidence: 99%

Deep learning for the estimation of water-levels using river cameras

Vandaele¹,

Dance²,

Ojha³

2021

Preprint

View full text Add to dashboard Cite

Abstract. River level estimation is a critical task required for the understanding of flood events, and is often complicated by the scarcity of available data. Recent studies have proposed to take advantage of large networks of river camera images to estimate the river levels, but currently, the utility of this approach remains limited as it requires a large amount of manual intervention (ground topographic surveys and water image annotation). We develop an approach using an automated water semantic segmentation method to ease the process of river level estimation from river camera images. Our method is based on the application of a transfer learning methodology to deep semantic neural networks designed for water segmentation. Using datasets of image series extracted from four river cameras and manually annotated for the observation of a flood event on the Severn and Avon rivers, UK (21 November–5 December 2012), we show that our algorithm is able to automate the annotation process with an accuracy greater than 91 %. Then, we apply our approach to year-long image series from the same cameras observing the Severn and Avon (from 1 June 2019 to 31 May 2020) and compare our results with nearby river-gauge measurements. Given the high correlation (Pearson's Correlation Coefficient > 0.94) between our results and the river-gauge measurements, it is clear that our approach to automation of the water segmentation on river camera images could allow for straightforward, inexpensive observation of flood events, especially at ungauged locations.

show abstract

Deep Transfer Learning for Art Classification Problems

Cited by 45 publications

References 27 publications

Automated Water Segmentation and River Level Detection on Camera Images Using Transfer Learning

Automated Water Segmentation and River Level Detection on Camera Images Using Transfer Learning

A Comprehensive Survey on Computational Aesthetic Evaluation of Visual Art Images: Metrics and Challenges

Deep learning for the estimation of water-levels using river cameras

Contact Info

Product

Resources

About