ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity
Authors:
- 1 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11906-11915
Abstract
We present ALADIN (All Layer AdaIN); a novel architecture for searching images based on the similarity of their artistic style. Representation learning is critical to visual search, where distance in the learned search embedding reflects image similarity. Learning an embedding that discriminates fine-grained variations in style is hard, due to the difficulty of defining and labelling style. ALADIN takes a weakly supervised approach to learning a representation for fine-grained style similarity of digital artworks, leveraging BAM-FG, a novel large-scale dataset of user generated content groupings gathered from the web. ALADIN sets a new state of the art accuracy for style-based visual search over both coarse labelled style data (BAM) and BAM-FG; a new 2.62 million image dataset of 310,000 fine-grained style groupings also contributed by this work.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Visual attribute transfer through deep image analogyACM Transactions on Graphics, 2017
- Image Style Transfer Using Convolutional Neural Networks2016
- Deep Residual Learning for Image Recognition2016
- Visualizing and Understanding Deep Texture Representations2016
- Learning visual similarity for product design with convolutional neural networksACM Transactions on Graphics, 2015
- Recognizing Image Style2014
- Combining randomization and discrimination for fine-grained image categorization2011
- Impressionism, expressionism, surrealismACM Transactions on Applied Perception, 2010
- Image analogies2001