CVAILGJun 21, 2021

Photozilla: A Large-Scale Photography Dataset and Visual Embedding for 20 Photography Styles

arXiv:2106.11359v15 citations
Originality Incremental advance
AI Analysis

This work addresses the need for automated style classification in digital photography, which is incremental as it builds on existing classification methods with a new dataset and adaptation technique.

The authors tackled the problem of classifying photography styles by introducing a large-scale dataset of over 990k images across 10 styles, achieving ~96% accuracy with classification models, and developed a novel Siamese-based network that adapts to unseen styles with only 25 training samples, achieving over 68% accuracy for 10 other styles.

The advent of social media platforms has been a catalyst for the development of digital photography that engendered a boom in vision applications. With this motivation, we introduce a large-scale dataset termed 'Photozilla', which includes over 990k images belonging to 10 different photographic styles. The dataset is then used to train 3 classification models to automatically classify the images into the relevant style which resulted in an accuracy of ~96%. With the rapid evolution of digital photography, we have seen new types of photography styles emerging at an exponential rate. On that account, we present a novel Siamese-based network that uses the trained classification models as the base architecture to adapt and classify unseen styles with only 25 training samples. We report an accuracy of over 68% for identifying 10 other distinct types of photography styles. This dataset can be found at https://trisha025.github.io/Photozilla/

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes