Smelly, dense, and spreaded: The Object Detection for Olfactory References (ODOR) dataset
This dataset addresses the need for robust computer vision in humanities applications by offering a more comprehensive and challenging resource for researchers in artwork analysis and cultural heritage.
The authors tackled the problem of object detection in artworks by creating the ODOR dataset with 38,116 object-level annotations across 4,712 images and 139 fine-grained categories, which features challenging properties like dense and overlapping objects. They provided baseline analyses and highlighted these difficulties to inspire research in artwork object detection and visual cultural heritage.
Real-world applications of computer vision in the humanities require algorithms to be robust against artistic abstraction, peripheral objects, and subtle differences between fine-grained target classes. Existing datasets provide instance-level annotations on artworks but are generally biased towards the image centre and limited with regard to detailed object classes. The proposed ODOR dataset fills this gap, offering 38,116 object-level annotations across 4712 images, spanning an extensive set of 139 fine-grained categories. Conducting a statistical analysis, we showcase challenging dataset properties, such as a detailed set of categories, dense and overlapping objects, and spatial distribution over the whole image canvas. Furthermore, we provide an extensive baseline analysis for object detection models and highlight the challenging properties of the dataset through a set of secondary studies. Inspiring further research on artwork object detection and broader visual cultural heritage studies, the dataset challenges researchers to explore the intersection of object recognition and smell perception.