Papers › Improving Object Detection in Art Images Using Only Style Transfer

Improving Object Detection in Art Images Using Only Style Transfer

12 Feb 2021arXiv:2102.06529archive 2025-07-28

David Kadish, Sebastian Risi, Anders Sundnes Løvlie

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

dkadish/Style-Transfer-for-Object-Detection-in-Art officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Object DetectionStyle Transferobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection PeopleArt FasterRCNN (trained on StyleCOCO) mAP 36 #5 of 6 Archive leaderboard report
Object Detection PeopleArt FasterRCNN (trained on StyleCOCO) mAP@0.5 68 #5 of 6 Archive leaderboard report
Object Detection PeopleArt FasterRCNN (trained on StyleCOCO) mAP@0.75 33 #5 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ConvolutionFaster R-CNNRPNRoIPoolSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections