mirlansmind / awesome-dinov2-extensions
This repo contains extensions to DINO V2 model by Meta, and awesome applications built on top of it.
☆39Updated last year
Alternatives and similar repositories for awesome-dinov2-extensions:
Users that are interested in awesome-dinov2-extensions are comparing it to the libraries listed below
- ☆63Updated last year
- [NeurIPS 2023] FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models☆129Updated last year
- [NeurIPS2022] This is the official implementation of the paper "Expediting Large-Scale Vision Transformer for Dense Prediction without Fi…☆83Updated last year
- Train InternViT-6B in MMSegmentation and MMDetection with DeepSpeed☆79Updated 3 months ago
- Distilling the powerful segment anything models into lightweight ones for efficient segmentation.☆29Updated last year
- Open-vocabulary Semantic Segmentation☆34Updated last year
- Official Implementation of ICCV 2023 Paper - SegPrompt: Boosting Open-World Segmentation via Category-level Prompt Learning☆109Updated 5 months ago
- [ECCV 2024] SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding☆49Updated 3 months ago
- [CVPR2022] "Progressive End-to-End Object Detection in Crowded Scenes" on Deformable-DETR.☆30Updated 2 years ago
- Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts (CVPR 2024)☆72Updated 4 months ago
- Baby-DALL3: Annotation anything in visual tasks and Generate anything just all in one-pipeline with GPT-4 (a small baby of DALL·E 3).☆82Updated last year
- Combining "segment-anything" with MOT, it create the era of "MOTS"☆152Updated last year
- OvarNet official implement of the paper "OvarNet: Towards Open-vocabulary Object Attribute Recognition"☆98Updated last year
- ☆25Updated 3 months ago
- ☆134Updated last year
- ☆104Updated 8 months ago
- Recognize Any Regions☆122Updated 2 months ago
- [CVPR 2024 Highlight] Official GraCo: Granularity-Controllable Interactive Segmentation.☆48Updated last month
- ☆38Updated 2 years ago
- Accelerate segment anything model inference using Tensorrt 8.6.1.6☆85Updated last year
- Collect some resource about Segment Anything (SAM), including the latest papers and demo☆113Updated last year
- 1st solution for the Webly-supervised Fine-grained Recognition competition in https://www.cvmart.net/race/10412/base☆34Updated last year
- A cli program of image retrieval using dinov2☆66Updated last year
- DiverGen (CVPR 2024) & BSGAL (ICML 2024)☆41Updated 3 months ago
- Codebase for the Recognize Anything Model (RAM)☆72Updated last year
- Adobe-EntitySeg dataset☆40Updated last year
- Unofficial implement of "Pix2seq: A Language Modeling Framework for Object Detection" on mmdetection☆31Updated 2 years ago
- A Siamese self-supervised pretraining approach for the Transformer architecture in DETR☆35Updated last year
- ☆19Updated last year
- PromptDet: Towards Open-vocabulary Detection using Uncurated Images, ECCV2022☆164Updated 2 years ago