X-AnyLabeling Releases

This is a minor bug fix and feature release for X-AnyLabeling v2.4.1. The update addresses two critical memory and state management issues while introducing new annotation capabilities. Users gain the ability to modify group_id through a dialog and export annotations in MOTS format.

Aug 29, 2024

X-AnyLabeling v2.4.0 is a major release featuring new AI model support including SAM2, GroundingSAM2, RT-DETRv2, RAM++, YOLOW-RAM++, and Depth-Anything v2, along with enhanced annotation capabilities for tracking, KIE linking, and various import/export formats. The update also includes UI improvements like continuous drawing mode, shape union, crosshair customization, and a refreshed application icon.

Jul 14, 2024

This is a bug fix and performance optimization release for X-AnyLabeling v2.3.6. The update addresses several issues including TypeErrors in YOLO models, ValueErrors related to shape selection, and a list index out of range bug when exporting DOTA annotations. The release also includes optimized brightness/contrast adjustment functionality.

May 25, 2024

v2.3.5 is a bug fix and enhancement release for X-AnyLabeling, an AI-powered image labeling tool. This update addresses critical issues including TypeError in YOLO models, IndexError in the Canvas widget, and Windows path handling. It also introduces performance optimizations for large image files and adds new features like obb-to-hbb conversion and enhanced image cropping with polygon and rotation support.

Apr 1, 2024

This release (v2.3.4) of X-AnyLabeling adds support for the YOLO-World visual language model and enables a label display feature. The update includes new executable builds for both CPU and GPU versions across Windows and Linux platforms.

Mar 16, 2024

This v2.3.3 release of X-AnyLabeling introduces YOLO-World model support for Visual Language Model tasks, along with several annotation workflow improvements including expanded sub-image save functionality, label format conversion capabilities, and real-time progress tracking for mask uploads.

Feb 27, 2024

This release adds YOLOv9 model support to X-AnyLabeling along with several usability improvements including horizontal-to-rotated bounding box conversion, label deletion/renaming capabilities, and quick tag correction functionality.

Feb 24, 2024

This is a minor release (v2.3.1) of X-AnyLabeling, an AI-powered labeling tool. The update introduces three key enhancements: the ability to save cropped rectangle shapes, a new CLIP+SAM model combination for improved semantic and spatial understanding, and support for the Depth Anything model in depth estimation tasks.

Jan 31, 2024

This release v2.3.0 of X-AnyLabeling adds support for new detection models including YOLOv8-OBB for oriented object detection, RTMDet and RTMO for object detection/pose estimation, and a Chinese license plate detection and recognition model based on YOLOv5.

Jan 13, 2024

X-AnyLabeling v2.2.0 is a significant update to this annotation tool, introducing major UI/UX improvements including a new status bar, background color rendering, and expanded editing capabilities. The release adds robust import/export support for multiple annotation formats and enhances the Segment Anything (SAM) annotation workflow.

Dec 26, 2023

This is a maintenance release providing updated executable binaries for X-AnyLabeling v2.1.0 across multiple platforms (Windows CPU/GPU and Linux CPU/GPU), accompanied by MD5 checksums for verification purposes.

Nov 24, 2023

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.

Nov 13, 2023

This release adds pose estimation capabilities using YOLOv8-Pose, introduces object-level tagging support with yolov5_ram, enables adjustment of image preprocessing parameters (keep_prev_brightness and keep_prev_contrast), and adds batch labeling for unknown categories using Grounding-DINO.

Nov 6, 2023

This is the v1.0.0 release of X-AnyLabeling, a labeling tool that introduces rotation box support and integrates several state-of-the-art models including YOLOv5-OBB for oriented bounding box detection, GroundingDINO for zero-shot object detection, and Recognize Anything for image tagging.

Oct 25, 2023

This release adds new object detection models (Gold-YOLO and DAMO-YOLO), introduces the OC_Sort multi-object tracking algorithm, and includes a new small object detection feature using SAHI. New executable versions for both CPU and GPU on Windows and Linux platforms are also provided.

Oct 10, 2023

This release v0.2.4 provides updated pre-built executables for both Windows and Linux platforms (CPU and GPU variants), along with adding support for the EfficientViT-SAM model for image segmentation tasks.

Sep 20, 2023

This release v0.2.3 introduces the YOLOv5-SAM model for enhanced auto-labeling capabilities and includes bug fixes for issues #51, #60, and #62. New executables are provided for both Windows and Linux platforms in CPU and GPU variants.

Sep 18, 2023

This v0.2.2 release provides new Windows and Linux executables (both CPU and GPU variants) with support for the PP-OCRv4 model and introduces a Model Lists feature for easier model management.

Sep 14, 2023

This release (v0.2.1) provides updated binary executables for X-AnyLabeling across multiple platforms, including Windows and Linux in both CPU and GPU variants. The release includes MD5 checksums for verifying the integrity of the downloaded files.

Sep 6, 2023

This release introduces multiple new AI models focused on medical image segmentation (MobileSAM, MedSAM, SAM-Med2D, LVM-Med) along with specialized medical datasets for polyp, skin lesion, and breast cancer segmentation. It also adds lane detection (CLRNet) and pose estimation (DWPose) capabilities, plus new platform-specific versions for CPU/GPU and Linux systems.

Aug 9, 2023