DeTr-TableDetection-5000-images Open-source Table Detection Model

Detr TableDetection 5000 Images

Developed by illuin

A table detection model fine-tuned based on facebook/detr-resnet-50, trained on the table_detection_light dataset

Downloads 247

Release Time : 2/2/2023

Model Overview

This model is used to detect table regions in images, implemented based on the DETR (Detection Transformer) architecture

Transformer-based Object Detection

Adopts the DETR architecture, avoiding complex anchor box designs and non-maximum suppression steps in traditional object detection methods

Lightweight Training Data

Fine-tuned with only 5000 images, suitable for resource-constrained application scenarios

End-to-End Training

Directly outputs detection results without complex post-processing steps

Table detection in images

Table region localization

Document Processing

PDF Document Analysis

Detect table regions from scanned PDF documents

Office Automation

Automatically identify table locations in documents for subsequent processing

Training Loss	Epoch	Step	Validation Loss	Mean Iou
0.741	1.0	313	0.7054	0.0259
0.5559	2.0	626	0.5159	0.0231
0.4213	3.0	939	0.4154	0.0254
0.4374	4.0	1252	0.4072	0.0249
0.3884	5.0	1565	0.4454	0.0232
0.4057	6.0	1878	0.4251	0.0249
0.3511	7.0	2191	0.3882	0.0239
0.3463	8.0	2504	0.3766	0.0243
0.3346	9.0	2817	0.4142	0.0236
0.3183	10.0	3130	0.3804	0.0242
0.3049	11.0	3443	0.3642	0.0244
0.2942	12.0	3756	0.3541	0.0253
0.2836	13.0	4069	0.3359	0.0252
0.2738	14.0	4382	0.3338	0.0254
0.2629	15.0	4695	0.3318	0.0267
0.2591	16.0	5008	0.3311	0.0224
0.2457	17.0	5321	0.3317	0.0234
0.2406	18.0	5634	0.3219	0.0238
0.2383	19.0	5947	0.3143	0.0238
0.2229	20.0	6260	0.3184	0.0234

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base