OmniArt: Multi-task Deep Learning for Artistic Data Analysis

Abstract

Vast amounts of artistic data is scattered on-line from both museums and art applications. Collecting, processing and studying it with respect to all accompanying attributes is an expensive process. With a motivation to speed up and improve the quality of categorical analysis in the artistic domain, in this paper we propose an efficient and accurate method for multi-task learning with a shared representation applied in the artistic domain. We continue to show how different multi-task configurations of our method behave on artistic data and outperform handcrafted feature approaches as well as convolutional neural networks. In addition to the method and analysis, we propose a challenge like nature to the new aggregated data set with almost half a million samples and structured meta-data to encourage further research and societal engagement.

9 pages, 6 figures, 4 tables

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation
• A Unified Perspective on Multi-Domain and Multi-Task Learning
• Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature
• Convolutional Sketch Inversion
• Detecting People in Cubist Art

Cited by in corpus (10)

• Hyperspherical Prototype Networks
• A deep learning approach to clustering visual arts
• Recognizing Characters in Art History Using Deep Learning
• Graph Neural Networks for Knowledge Enhanced Visual Representation of Paintings
• Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning
• Do Better ImageNet Models Transfer Better... for Image Recommendation?
• Historical and Modern Features for Buddha Statue Classification
• Materials In Paintings (MIP): An interdisciplinary dataset for perception, art history, and computer vision
• Multi-Class Zero-Shot Learning for Artistic Material Recognition
• HyperLearn: A Distributed Approach for Representation Learning in Datasets With Many Modalities