facebookresearch / ov-seg
This is the official PyTorch implementation of the paper Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP.
☆676Updated 11 months ago
Related projects: ⓘ
- [ICCV 2023] Official implementation of the paper "A Simple Framework for Open-Vocabulary Segmentation and Detection"☆637Updated 7 months ago
- Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]☆845Updated 2 months ago
- Segment-anything related awesome extensions/projects/repos.☆340Updated last year
- [ICLR'24] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching☆422Updated last month
- [ECCV 2024] Tokenize Anything via Prompting☆502Updated 2 months ago
- [CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segme…☆1,153Updated 8 months ago
- Grounded Segment Anything: From Objects to Parts☆383Updated last year
- Experiment on combining CLIP with SAM to do open-vocabulary image segmentation.☆331Updated last year
- [CVPR 2023] Official Implementation of X-Decoder for generalized decoding for pixel, image and language☆1,281Updated 11 months ago
- Fine-tune Segment-Anything Model with Lightning Fabric.☆482Updated 5 months ago
- Language-Driven Semantic Segmentation☆705Updated 2 months ago
- Open-vocabulary Semantic Segmentation☆295Updated 4 months ago
- CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks☆346Updated last year
- [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"☆2,255Updated 2 months ago
- [CVPR 2024] Alpha-CLIP: A CLIP Model Focusing on Wherever You Want☆639Updated last month
- Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation☆365Updated 4 months ago
- OneFormer: One Transformer to Rule Universal Image Segmentation, arxiv 2022 / CVPR 2023☆1,440Updated 10 months ago
- [CVPR 2022] Official code for "RegionCLIP: Region-based Language-Image Pretraining"☆696Updated 5 months ago
- [ICCV2023] VLPart: Going Denser with Open-Vocabulary Part Segmentation☆349Updated last year
- [CVPR 2024] Official implementation of the paper "Visual In-context Learning"☆363Updated 5 months ago
- This repository is for the first comprehensive survey on Meta AI's Segment Anything Model (SAM).☆765Updated this week
- Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds☆1,493Updated last month
- Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scena…☆754Updated last year
- Relate Anything Model is capable of taking an image as input and utilizing SAM to identify the corresponding mask within the image.☆438Updated last year
- Segment Anything combined with CLIP☆328Updated 7 months ago
- Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts☆980Updated last month
- Grounded Language-Image Pre-training☆2,154Updated 7 months ago
- This is an implementation of zero-shot instance segmentation using Segment Anything.☆295Updated last year
- Code release for our CVPR 2023 paper "Detecting Everything in the Open World: Towards Universal Object Detection".☆526Updated last year
- Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2☆710Updated last week