Tracking by HBB Detection	Tracking by OBB Detection
Tracking by Instance Segmentation	Tracking by Pose Estimation

• Support GeCo zero-shot counting model
• For more details, please refer to the Changelog

X-AnyLabeling is a powerful annotation tool that integrates an AI engine for fast and automatic labeling. It’s designed for visual data engineers, offering industrial-grade solutions for complex tasks.

• Processes both images and videos.
• Accelerates inference with GPU support.
• Allows custom models and secondary development.
• Supports one-click inference for all images in the current task.
• Enable import/export for formats like COCO, VOC, YOLO, DOTA, MOT, MASK, PPOCR.
• Handles tasks like classification, detection, segmentation, caption, rotation, tracking, estimation, ocr and so on.
• Supports diverse annotation styles: polygons, rectangles, rotated boxes, circles, lines, points, and annotations for text detection, recognition, and KIE.

Object Detection	SOD with SAHI	Facial Landmark Detection	Pose Estimation
Lane Detection	OCR	MOT	Instance Segmentation
Tagging	Grounding	Recognition	Rotation
Segment Anything	BC-SAM	Skin-SAM	Polyp-SAM

For more details, please refer to 👉 model_zoo 👈

1. Installation & Quickstart
2. Usage
3. Customize a model

• Classification
  • Image-Level
  • Shape-Level
• Detection
  • HBB Object Detection
  • OBB Object Detection
• Segmentation
  • Instance Segmentation
  • Binary Semantic Segmentation
  • Multiclass Semantic Segmentation
• Description
  • Tagging
  • Captioning
• Estimation
  • Pose Estimation
  • Depth Estimation
• OCR
  • Text Recognition
  • Key Information Extraction
• MOT
  • Tracking by HBB Object Detection
  • Tracking by OBB Object Detection
  • Tracking by Instance Segmentation
  • Tracking by Pose Estimation
• iVOS
• Matting
  • Image Matting
• Vision-Language
  • Florence 2
• Counting
  • GeCo

If you find this project helpful, please give it a ⭐star⭐, and for any questions or issues, feel free to create an issue or email cv_hub@163.com.

This project is released under the GPL-3.0 license.

I extend my heartfelt thanks to the developers and contributors of AnyLabeling, LabelMe, LabelImg, roLabelImg, PPOCRLabel and CVAT, whose work has been crucial to the success of this project.

If you use this software in your research, please cite it as below:

@misc{X-AnyLabeling,
  year = {2023},
  author = {Wei Wang},
  publisher = {Github},
  organization = {CVHub},
  journal = {Github repository},
  title = {Advanced Auto Labeling Solution with Added Features},
  howpublished = {\url{https://github.com/CVHub520/X-AnyLabeling}}
}