Napredna pretraga

Pregled bibliografske jedinice broj: 952560

Fine-tuning Convolutional Neural Networks for fine art classification

Cetinić, Eva; Lipić, Tomislav; Grgić, Sonja
Fine-tuning Convolutional Neural Networks for fine art classification // Expert systems with applications, 114 (2018), 107-118 doi:10.1016/j.eswa.2018.07.026 (međunarodna recenzija, članak, znanstveni)

Fine-tuning Convolutional Neural Networks for fine art classification

Cetinić, Eva ; Lipić, Tomislav ; Grgić, Sonja

Expert systems with applications (0957-4174) 114 (2018); 107-118

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Painting classification ; Deep learning ; Convolutional Neural Networks ; Fine-tuning strategies

The increasing availability of large digitized fine art collections opens new research perspectives in the intersection of artificial intelligence and art history. Motivated by the successful performance of Convolutional Neural Networks (CNN) for a wide variety of computer vision tasks, in this paper we explore their applicability for art-related image classification tasks. We perform extensive CNN fine-tuning experiments and consolidate in one place the results for five different art- related classification tasks on three large fine art datasets. Along with addressing the previously explored tasks of artist, genre, style and time period classification, we introduce a novel task of classifying artworks based on their association with a specific national artistic context. We present state-of- the-art classification results of the addressed tasks, signifying the impact of our method on computational analysis of art, as well as other image classification related research areas. Furthermore, in order to question transferability of deep representations across various source and target domains, we systematically compare the effects of domain- specific weight initialization by evaluating networks pre-trained for different tasks, varying from object and scene recognition to sentiment and memorability labelling. We show that fine-tuning networks pre-trained for scene recognition and sentiment prediction yields better results than fine-tuning networks pre- trained for object recognition. This novel outcome of our work suggests that the semantic correlation between different domains could be inherent in the CNN weights. Additionally, we address the practical applicability of our results by analysing different aspects of image similarity. We show that features derived from fine-tuned networks can be employed to retrieve images similar in either style or content, which can be used to enhance capabilities of search systems in different online art collections.

Izvorni jezik

Znanstvena područja


Fakultet elektrotehnike i računarstva, Zagreb,
Institut "Ruđer Bošković", Zagreb

Časopis indeksira:

  • Current Contents Connect (CCC)
  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus