# Improving Object Detection in Art Images Using Only Style Transfer

arXiv: https://arxiv.org/abs/2102.06529 · HTML: https://mlsanity.com/paper/2102.06529/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 26 references that are in the map.
- First posted on arXiv 12 Feb 2021.

## Builds on (most cited first, 12 of 12)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases](https://mlsanity.com/paper/2010.15052/) (2020)
- [BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography](https://mlsanity.com/paper/1704.08614/) (2017)
- [Detecting People in Artwork with CNNs](https://mlsanity.com/paper/1610.08871/) (2016)
- [Auditing ImageNet: Towards a Model-driven Framework for Annotating Demographic Attributes of Large-Scale Image Datasets](https://mlsanity.com/paper/1905.01347/) (2019)
- [The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs](https://mlsanity.com/paper/1505.00110/) (2015)
- [Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts](https://mlsanity.com/paper/2008.01178/) (2020)
- [Artistic Domain Generalisation Methods are Limited by their Deep Representations](https://mlsanity.com/paper/1907.12622/) (2019)

## Built on by (most cited first, 15 of 15)

- [Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes](https://mlsanity.com/paper/2303.02760/) (2023)
- [DEArt: Dataset of European Art](https://mlsanity.com/paper/2211.01226/) (2022)
- [ArtMentor: AI-Assisted Evaluation of Artworks to Explore Multimodal Large Language Models Capabilities](https://mlsanity.com/paper/2502.13832/) (2025)
- [Semi-supervised Human Pose Estimation in Art-historical Images](https://mlsanity.com/paper/2207.02976/) (2022)
- [Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History](https://mlsanity.com/paper/2301.05124/) (2023)
- [SniffyArt: The Dataset of Smelling Persons](https://mlsanity.com/paper/2311.11888/) (2023)
- [Automatic Modeling of Social Concepts Evoked by Art Images as Multimodal Frames](https://mlsanity.com/paper/2110.07420/) (2021)
- [Algorithmic Ways of Seeing: Using Object Detection to Facilitate Art Exploration](https://mlsanity.com/paper/2403.19174/) (2024)
- [Under the Skin of Foundation NFT Auctions](https://mlsanity.com/paper/2109.12321/) (2021)
- [Context-Infused Visual Grounding for Art](https://mlsanity.com/paper/2410.12369/) (2024)
- [Smelly, dense, and spreaded: The Object Detection for Olfactory References (ODOR) dataset](https://mlsanity.com/paper/2507.08384/) (2025)
- [Artificial Intelligence for Geometry-Based Feature Extraction, Analysis and Synthesis in Artistic Images: A Survey](https://mlsanity.com/paper/2412.01450/) (2024)
- [IBURD: Image Blending for Underwater Robotic Detection](https://mlsanity.com/paper/2502.17706/) (2025)
- [FDWST: Fingerphoto Deblurring using Wavelet Style Transfer](https://mlsanity.com/paper/2407.15964/) (2024)
- [ArtContext: Contextualizing Artworks with Open-Access Art History Articles and Wikidata Knowledge through a LoRA-Tuned CLIP Model](https://mlsanity.com/paper/2602.11349/) (2026)

## Abstract (arXiv)

Despite recent advances in object detection using deep learning neural networks, these neural networks still struggle to identify objects in art images such as paintings and drawings. This challenge is known as the cross depiction problem and it stems in part from the tendency of neural networks to prioritize identification of an object's texture over its shape. In this paper we propose and evaluate a process for training neural networks to localize objects - specifically people - in art images. We generate a large dataset for training and validation by modifying the images in the COCO dataset using AdaIn style transfer. This dataset is used to fine-tune a Faster R-CNN object detection network, which is then tested on the existing People-Art testing dataset. The result is a significant improvement on the state of the art and a new way forward for creating datasets to train neural networks to process art images.