This family of YOLO object detection models detects and classifies seven types of visual content in historical newspaper pages from the Library of Congress's Chronicling America collection.
Trained on the crowdsourced Beyond Words dataset these models identify:
Photographs
Illustrations
Maps
Comics/Cartoons
Editorial Cartoons
Headlines
Advertisements
Example Outputs
Below are two examples of the model's output. The first is an example from the training data, and the second is an example of the model's performance on an out-of-domain (OoD) image.
Successful detection example
Objects detected for an example from the training data
OoD example
Objects detected for an in the "wild" newspaper example
🚀 Quick Start
Installation
pip install ultralytics huggingface_hub
Inference
python
1from huggingface_hub import hf_hub_download
2from ultralytics import YOLO
34# Download and load nano model5model = YOLO(hf_hub_download(6 repo_id="small-models-for-glam/historic-newspaper-illustrations-yolov11",7 filename="yolo11n.pt"8))910# Or download and load small model11model = YOLO(hf_hub_download(12 repo_id="small-models-for-glam/historic-newspaper-illustrations-yolov11",13 filename="yolo11s.pt"14))1516# Run inference on an image17results = model("path/to/newspaper_page.jpg")1819# Process results20for result in results:21 boxes = result.boxes # Boxes object for bbox outputs22for box in boxes:23# Get box coordinates24 x1, y1, x2, y2 = box.xyxy[0]25# Get confidence score26 conf = box.conf[0]27# Get class28 cls = box.cls[0]29# Get class name30 class_name = model.names[int(cls)]31print(f"Detected {class_name} with confidence {conf:.2f}")
📰 Use Case
The model is intended to extract visual content from historical newspapers.
📊 Dataset
The models were trained on the Beyond Words dataset, which was created via crowdsourcing and augmented with expert-labelled annotations for headlines and advertisements. The dataset consists of:
3,559 annotated newspaper pages (train+val)
48,409 labelled visual content regions
7 content categories
Annotations are provided in COCO format and were aligned with METS/ALTO OCR for further downstream use.
It's important to note that the training data does not represent a representative sample of historical newspaper content. The training data is drawn from the Library of Congress's Chronicling America collection, which is focused on American newspapers from the late 19th and early 20th centuries. This also means that the models are likely to do much better on images from this period and digitised similarly.
🧠 Model Details
All models are fine-tuned variants of the YOLO11 object detection architecture. The training set consisted of high-resolution historical newspaper scans from WWI-era publications, with performance validated on a held-out set of 712 pages.
🔎 Performance Metrics
Class
Precision
Recall
mAP@0.5
mAP@0.5:0.95
Photograph
0.995
0.976
0.987
0.958
Illustration
0.990
0.969
0.983
0.929
Map
0.978
0.971
0.979
0.945
Comics/Cartoon
0.994
0.967
0.975
0.952
Editorial Cartoon
1.000
0.984
0.995
0.985
Headline
0.987
0.996
0.995
0.895
Advertisement
0.994
0.998
0.995
0.956
Overall (macro)
0.991
0.980
0.987
0.946
🧪 Model Variants
yolo11n.pt (nano)
Trained for edge applications or fast inference.
Results
Class
Precision
Recall
mAP@0.5
mAP@0.5:0.95
Photograph
0.995
0.976
0.987
0.958
Illustration
0.990
0.969
0.983
0.929
Map
0.978
0.971
0.979
0.945
Comics/Cartoon
0.994
0.967
0.975
0.952
Editorial Cartoon
1.000
0.984
0.995
0.985
Headline
0.987
0.996
0.995
0.895
Advertisement
0.994
0.998
0.995
0.956
Overall (macro)
0.991
0.980
0.987
0.946
yolo11s.pt (small)
Balanced for speed and accuracy.
Results
Class
Images
Instances
Box(P)
Box(R)
mAP50
mAP50-95
all
711
9923
0.98
0.958
0.982
0.927
Photograph
488
875
0.986
0.947
0.982
0.941
Illustration
154
206
0.962
0.951
0.972
0.906
Map
32
34
0.966
0.941
0.973
0.937
Comics/Cartoon
109
211
0.985
0.942
0.968
0.923
Editorial Cartoon
53
54
1.000
0.967
0.995
0.973
Headline
617
5685
0.979
0.966
0.992
0.868
Advertisement
510
2858
0.985
0.989
0.994
0.939
📂 Training
The models were trained using PyTorch and Ultralytics YOLOv11 on annotated newspaper pages. OCR-aligned captions were included in bounding boxes when present. Data augmentation techniques include resizing and random flipping.
🧾 Citation
If you use this model or dataset, please cite the following:
Model
bibtex
1@software{yolo11_ultralytics,
2 author = {Glenn Jocher and Jing Qiu},
3 title = {Ultralytics YOLO11},
4 version = {11.0.0},
5 year = {2024},
6 url = {https://github.com/ultralytics/ultralytics},
7 license = {AGPL-3.0}
8}
Dataset
bibtex
1@inproceedings{10.1145/3340531.3412767,
2 author = {Lee, Benjamin Charles Germain and Mears, Jaime and Jakeway, Eileen and Ferriter, Meghan and Adams, Chris and Yarasavage, Nathan and Thomas, Deborah and Zwaard, Kate and Weld, Daniel S.},
3 title = {The Newspaper Navigator Dataset: Extracting Headlines and Visual Content from 16 Million Historic Newspaper Pages in Chronicling America},
4 year = {2020},
5 publisher = {Association for Computing Machinery},
6 address = {New York, NY, USA},
7 doi = {10.1145/3340531.3412767},
8 url = {https://doi.org/10.1145/3340531.3412767}
9}
License
This model is released under the AGPL-3.0 license. The dataset is licensed CC0 (Public Domain).
