Starstruk Logo MarkStarstruk

v2.0.0

CVHub520/X-AnyLabelingv2.0.0Nov 13, 2023by CVHub520

AI Summary

This is the v2.0.0 major release of X-AnyLabeling, an AI-powered labeling tool. The release introduces Grounding-SAM which combines GroundingDINO with HQ-SAM for zero-shot high-quality predictions, enhanced HQ-SAM support, and new multi-label classification models for person and vehicle attributes.

Key Highlights

  • Release of X-AnyLabeling v2.0.0 with new executables for Windows (CPU/GPU) and Linux (CPU/GPU)
  • New Grounding-SAM support combining GroundingDINO and HQ-SAM for sota zero-shot predictions
  • Enhanced HQ-SAM for high-quality mask predictions
  • Added PersonAttribute and VehicleAttribute models for multi-label classification
  • New multi-label attribute annotation functionality

New Features

  • Grounding-SAM integration (GroundingDINO + HQ-SAM combination)
  • Enhanced HQ-SAM high-quality mask prediction support
  • PersonAttribute model for multi-label classification
  • VehicleAttribute model for multi-label classification
  • Multi-label attribute annotation functionality

Full Release Notes

## New versions

- X-AnyLabeling-CPU.exe [md5 | 23d042d22a0a1907c2cc9f19ecdc7657]
- X-AnyLabeling-GPU.exe [md5 | af8ec0ae720a24cc608090429bc9492d]
- X-Anylabeling-Linux-CPU [md5 | 8937539d2b073e66654cf3ebdce9c784]
- X-Anylabeling-Linux-GPU [md5 | 035fe58c13a15387ebb77f3066173a45]

## New feature
  - 🤗🤗🤗 Release the latest version [2.0.0](https://github.com/CVHub520/X-AnyLabeling/releases/tag/v2.0.0).
  - 🔥🔥🔥 Added support for Grounding-SAM, combining [GroundingDINO](https://github.com/wenyi5608/GroundingDINO) with [HQ-SAM](https://github.com/SysCV/sam-hq) to achieve sota zero-shot high-quality predictions!
  - 🚀🚀🚀 Enhanced support for [HQ-SAM](https://github.com/SysCV/sam-hq) model to achieve high-quality mask predictions.
  - 🙌🙌🙌 Support the [PersonAttribute](https://github.com/PaddlePaddle/PaddleClas/blob/release%2F2.5/docs/en/PULC/PULC_person_attribute_en.md) and [VehicleAttribute](https://github.com/PaddlePaddle/PaddleClas/blob/release%2F2.5/docs/en/PULC/PULC_vehicle_attribute_en.md) model for multi-label classification task.
  - 🆕🆕🆕 Introducing a new multi-label attribute annotation functionality.