xuwangyin / dinov2-finetuneLinks
Finetuning DINOv2 (https://github.com/facebookresearch/dinov2) on your own dataset
☆62Updated 2 years ago
Alternatives and similar repositories for dinov2-finetune
Users that are interested in dinov2-finetune are comparing it to the libraries listed below
Sorting:
- [CVPR 2024] Code for "Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adapta…☆172Updated last year
- The official implementation of “Segment Anything Model is a Good Teacher for Local Feature Learning”.☆118Updated 2 months ago
- Downstream-Dino-V2: A GitHub repository featuring an easy-to-use implementation of the DINOv2 model by Facebook for downstream tasks such…☆248Updated 2 years ago
- Testing adaptation of the DINOv2 encoder for vision tasks with Low-Rank Adaptation (LoRA)☆164Updated last year
- ☆36Updated 10 months ago
- [TPAMI 2025] UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation☆155Updated 7 months ago
- ☆44Updated 10 months ago
- Code Release for MaskCLIP (ICML 2023)☆69Updated last year
- [CVPR 2024 Highlight] Official GraCo: Granularity-Controllable Interactive Segmentation.☆58Updated 5 months ago
- [ECCV 2024 Oral] The official implementation of "CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model".☆133Updated 11 months ago
- The application of large pre-trained vision model DINOv2 from MetaAI for feature points matching, and a ViT decoder used for Auto Encoder☆17Updated 2 years ago
- [ECCV2024] Official implementation of Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes☆89Updated 3 months ago
- ☆70Updated last year
- Segment Your Ring (SYR) - Segment Anything model adapted with LoRA to segment rings.☆121Updated last year
- [ICLR'24] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching☆510Updated 8 months ago
- Unofficial edge detection implementation using the Automatic Mask Generation (AMG) of the Segment Anything Model (SAM).☆74Updated 2 months ago
- Segment Anything Model, SAM, Sonar images☆67Updated last year
- 将Mask2Former的backbone替换成DINOv2训练好的ViT模型☆28Updated 2 years ago
- This repo aims to include materials (papers, codes, slides) about SAM2 (segment anything in images and videos). We are continuously impro…☆98Updated last week
- PyTorch code and models for the DINOv2 self-supervised learning method, own data set and own adapted training.☆69Updated last year
- ☆89Updated last year
- [CVPR 2023] Official implementation of the paper: MP-Former: Mask-Piloted Transformer for Image Segmentation☆129Updated last year
- ☆93Updated last year
- ☆154Updated last year
- [CVPR 2024] PEM: Prototype-based Efficient MaskFormer for Image Segmentation☆113Updated 5 months ago
- The official implementation of "Segment Anything with Multiple Modalities".☆99Updated 11 months ago
- X-SAM: From Segment Anything to Any Segmentation☆95Updated last week
- Loss Functions in the Era of Semantic Segmentation: A Survey and Outlook☆60Updated last year
- Training and testing of DINOv2 for segmentation downstream☆39Updated 6 months ago
- ☆19Updated last year