x-anylabeling-cvhub 3.3.2

Advanced Auto Labeling Solution with Added Features

English | 简体中文

Auto-Labeling

Text/Visual Prompting and Prompt-free for Detection & Segmentation

Detect Anything

Segment Anything

Chatbot

VQA

Image Classifier

🥳 What's New

• Bump version to v3.3.2
• Add support for Segment Anything 3 model with text and visual promptable segmentation (#1207)
• Add depth calibration feature for Depth Anything models (#1201)
• For more details, please refer to the CHANGELOG

X-AnyLabeling

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

Also, we developed X-AnyLabeling-Server, a simple, lightweight, and extensible serving framework that enables remote inference capabilities for X-AnyLabeling. Feel free to try it out.

Features

• Supports remote inference service.
• 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.
• Supports import/export for formats like COCO, VOC, YOLO, DOTA, MOT, MASK, PPOCR, MMGD, VLM-R1.
• 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.

Model library

Task Category	Supported Models
🖼️ Image Classification	YOLOv5-Cls, YOLOv8-Cls, YOLO11-Cls, InternImage, PULC
🎯 Object Detection	YOLOv5/6/7/8/9/10, YOLO11/12, YOLOX, YOLO-NAS, D-FINE, DAMO-YOLO, Gold_YOLO, RT-DETR, RF-DETR, DEIMv2
🖌️ Instance Segmentation	YOLOv5-Seg, YOLOv8-Seg, YOLO11-Seg, Hyper-YOLO-Seg, RF-DETR-Seg
🏃 Pose Estimation	YOLOv8-Pose, YOLO11-Pose, DWPose, RTMO
👣 Tracking	Bot-SORT, ByteTrack
🔄 Rotated Object Detection	YOLOv5-Obb, YOLOv8-Obb, YOLO11-Obb
📏 Depth Estimation	Depth Anything
🧩 Segment Anything	SAM 1/2/3, SAM-HQ, SAM-Med2D, EdgeSAM, EfficientViT-SAM, MobileSAM
✂️ Image Matting	RMBG 1.4/2.0
💡 Proposal	UPN
🏷️ Tagging	RAM, RAM++
📄 OCR	PP-OCRv4, PP-OCRv5
🗣️ Vision Foundation Models	Florence2
👁️ Vision Language Models	Qwen3-VL, Gemini, ChatGPT
🛣️ Land Detection	CLRNet
📍 Grounding	CountGD, GeCO, Grounding DINO, YOLO-World, YOLOE
📚 Other	👉 model_zoo 👈

Docs

0. Remote Inference Service
1. Installation & Quickstart
2. Usage
3. Command Line Interface
4. Customize a model
5. Chatbot
6. VQA
7. Multi-class Image Classifier

Examples

• 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
• Grounding
  • YOLOE
  • SAM 3
• Training
  • Ultralytics

Contribute

We believe in open collaboration! X‑AnyLabeling continues to grow with the support of the community. Whether you're fixing bugs, improving documentation, or adding new features, your contributions make a real impact.

To get started, please read our Contributing Guide and make sure to agree to the Contributor License Agreement (CLA) before submitting a pull request.

If you find this project helpful, please consider giving it a ⭐️ star! Have questions or suggestions? Open an issue or email us at [e-mail].

A huge thank you 🙏 to everyone helping to make X‑AnyLabeling better.

License

This project is licensed under the GPL-3.0 license and is only free to use for personal non-commercial purposes. For academic, research, or educational use, it is also free but requires registration via this form here. If you intend to use this project for commercial purposes or within a company, please contact [e-mail] to obtain a commercial license.

Acknowledgement

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.

Citing

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}}
}

---

🔝 Back to Top