Novel Artistic Scene-Centric Datasets for Effective Transfer Learning in Fragrant Spaces
This work addresses the challenge of analyzing olfactory scenes in cultural heritage for researchers, though it is incremental in applying existing methods to a new domain.
The paper tackled the problem of classifying fragrant spaces and artistic scenes by applying transfer learning with weakly labeled data from cultural heritage sources, achieving improved classification results as evaluated on manually corrected test splits.
Olfaction, often overlooked in cultural heritage studies, holds profound significance in shaping human experiences and identities. Examining historical depictions of olfactory scenes can offer valuable insights into the role of smells in history. We show that a transfer-learning approach using weakly labeled training data can remarkably improve the classification of fragrant spaces and, more generally, artistic scene depictions. We fine-tune Places365-pre-trained models by querying two cultural heritage data sources and using the search terms as supervision signal. The models are evaluated on two manually corrected test splits. This work lays a foundation for further exploration of fragrant spaces recognition and artistic scene classification. All images and labels are released as the ArtPlaces dataset at https://zenodo.org/doi/10.5281/zenodo.11584328.