autodistill / autodistill-grounded-sam-2Links
Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.
☆124Updated 9 months ago
Alternatives and similar repositories for autodistill-grounded-sam-2
Users that are interested in autodistill-grounded-sam-2 are comparing it to the libraries listed below
Sorting:
- Referring any person or objects given a natural language description. Code base for RexSeek and HumanRef Benchmark☆132Updated last month
- Official Code for Tracking Any Object Amodally☆118Updated 10 months ago
- Use Florence 2 to auto-label data for use in training fine-tuned object detection models.☆64Updated 9 months ago
- Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"☆413Updated 2 months ago
- EdgeSAM model for use with Autodistill.☆26Updated 11 months ago
- [ICCV2023] Segment Every Reference Object in Spatial and Temporal Spaces☆239Updated 3 months ago
- [ECCV 2024 & NeurIPS 2024] Official implementation of the paper TAPTR & TAPTRv2 & TAPTRv3☆263Updated 5 months ago
- Odd-One-Out: Anomaly Detection by Comparing with Neighbors (CVPR25)☆40Updated 6 months ago
- ☆40Updated 4 months ago
- ☆71Updated last month
- Evaluate the performance of computer vision models and prompts for zero-shot models (Grounding DINO, CLIP, BLIP, DINOv2, ImageBind, model…☆36Updated last year
- [ICLR 2025 oral] RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything☆249Updated last month
- [CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"☆296Updated last month
- Scaling Vision Pre-Training to 4K Resolution☆162Updated this week
- Muggled SAM: Segmentation without the magic☆139Updated last month
- YOLO-World + EfficientViT SAM☆98Updated last year
- Codebase for the Recognize Anything Model (RAM)☆79Updated last year
- RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)☆350Updated 9 months ago
- SSA + FastSAM/Semantic Fast Segment Anything , or Fast Semantic Segment Anything☆100Updated this week
- This method uses Segment Anything and CLIP to ground and count any object that matches a custom text prompt, without requiring any point …☆158Updated 2 years ago
- [NeurIPS 2023] HASSOD: Hierarchical Adaptive Self-Supervised Object Detection☆56Updated last year
- [CVPR25] Official repository for the paper: "SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation"☆186Updated last week
- Florence-2 is a novel vision foundation model with a unified, prompt-based representation for a variety of computer vision and vision-lan…☆61Updated 11 months ago
- ☆71Updated last month
- ClickDiffusion: Harnessing LLMs for Interactive Precise Image Editing☆69Updated last year
- Pytorch Implementation of "SMITE: Segment Me In TimE" (ICLR 2025)☆209Updated 2 months ago
- AutoTrackAnything is a universal, flexible and interactive tool for insane automatic object tracking over thousands of frames. It is deve…☆81Updated last year
- ☆23Updated 7 months ago
- [ACCV 2024 (Oral)] Official Implementation of "Moving Object Segmentation: All You Need Is SAM (and Flow)" Junyu Xie, Charig Yang, Weidi …☆307Updated 5 months ago
- [NeurIPS 2024] SlimSAM: 0.1% Data Makes Segment Anything Slim☆328Updated 3 months ago