Smelly, dense, and spreaded: The Object Detection for Olfactory References (ODOR) dataset
Preprint
Abstract
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.Keywords
All Related Versions
- Version 1, 2025-07-11, ArXiv
- Published version: Expert Systems with Applications, 255.
This publication has 30 references indexed in Scilit:
- Grounding DINO: Marrying DINO with Grounded Pre-training for Open-Set Object Detection2024
- ICC++: Explainable feature learning for art history using image compositionsPattern Recognition, 2022
- Data-efficient image captioning of fine art paintings via virtual-real semantic alignment trainingNeurocomputing, 2022
- A survey and performance evaluation of deep learning methods for small object detectionExpert Systems with Applications, 2021
- Feature Pyramid Networks for Object Detection2017
- YOLO9000: Better, Faster, Stronger2017
- Scene Parsing through ADE20K Dataset2017
- Aggregated Residual Transformations for Deep Neural Networks2017
- Cross-depiction problem: Recognition and synthesis of photographs and artworkComputational Visual Media, 2015
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009