bengaliAI/badlad-frcnn-paper

BaDLAD Faster R-CNN — Paper Baseline

Faster R-CNN R-50-FPN trained on the BaDLAD training set for Bengali document layout analysis (bounding-box track). Companion to the Mask R-CNN baseline bengaliAI/badlad-mrcnn-paper.

Paper: BaDLAD (ICDAR 2023)

Code: BengaliAI/BADLAD

Dataset: BaDLAD on Kaggle

Model Details

Field	Value
Architecture	Faster R-CNN R-50-FPN 3x
Framework	Detectron2
Config	COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml
Classes	paragraph, text_box, image, table (4)
Training data	BaDLAD train (~20 365 images)
Iterations	10 000 (paper recipe)
Outputs	class + bounding box (no mask head)
Checkpoint	model_final.pth (~159 MB)
sha256	bd507afaadb80585edada54e7303cef825bc0297e48ee1e08c863fc45751e2ef

Training recipe follows the Detectron settings in the paper (10k iterations, lr 0.001, batch 48) and BadLad_trainer_faster_rcnn.ipynb in the code repo.

Usage

from detectron2 import model_zoo
from detectron2.config import get_cfg
from detectron2.engine import DefaultPredictor
from huggingface_hub import hf_hub_download

weights = hf_hub_download("bengaliAI/badlad-frcnn-paper", "model_final.pth")

cfg = get_cfg()
cfg.merge_from_file(
    model_zoo.get_config_file("COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml")
)
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 4
cfg.MODEL.WEIGHTS = weights
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.05
predictor = DefaultPredictor(cfg)

Related models

Repo	Role
bengaliAI/badlad-mrcnn-paper	Mask R-CNN (instance segmentation)
bengaliAI/badlad-yolov8m-seg	YOLOv8m-seg layout model

Citation

@inproceedings{shihab2023badlad,
    title     = {{BaDLAD}: A Large Multi-Domain {Bengali} Document Layout Analysis Dataset},
    author    = {Shihab, Md. Istiak Hossain and Hasan, Md. Rakibul and Emon, Mahfuzur Rahman and Hossen, Syed Mobassir and Ansary, Md. Nazmuddoha and Ahmed, Intesur and Rakib, Fazle Rabbi and Dhruvo, Shahriar Elahi and Dip, Souhardya Saha and Pavel, Akib Hasan and Meghla, Marsia Haque and Haque, Md. Rezwanul and Chowdhury, Sayma Sultana and Sadeque, Farig and Reasat, Tahsin and Humayun, Ahmed Imtiaz and Sushmit, Asif Shahriyar},
    booktitle = {Proceedings of the 17th International Conference on Document Analysis and Recognition (ICDAR)},
    year      = {2023},
    url       = {https://arxiv.org/abs/2303.05325},
}