facebookresearch / ov-seg
This is the official PyTorch implementation of the paper Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP.
☆722Updated last year
Alternatives and similar repositories for ov-seg:
Users that are interested in ov-seg are comparing it to the libraries listed below
- [ICCV 2023] Official implementation of the paper "A Simple Framework for Open-Vocabulary Segmentation and Detection"☆708Updated last year
- Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]☆901Updated 10 months ago
- [CVPR 2023] Official Implementation of X-Decoder for generalized decoding for pixel, image and language☆1,313Updated last year
- [CVPR 2024] Official implementation of the paper "Visual In-context Learning"☆466Updated last year
- [ICLR'24] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching☆491Updated 4 months ago
- [CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segme…☆1,311Updated last year
- CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks☆415Updated 2 months ago
- [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"☆2,604Updated 9 months ago
- Open-vocabulary Semantic Segmentation☆342Updated 6 months ago
- Experiment on combining CLIP with SAM to do open-vocabulary image segmentation.☆367Updated 2 years ago
- [ECCV 2024] Tokenize Anything via Prompting☆583Updated 4 months ago
- [ICCV2023] VLPart: Going Denser with Open-Vocabulary Part Segmentation☆374Updated last year
- Grounded Segment Anything: From Objects to Parts☆408Updated last year
- Segment Any RGBD☆823Updated last year
- Fine-tune Segment-Anything Model with Lightning Fabric.☆539Updated last year
- Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation☆407Updated last year
- Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds☆1,575Updated 9 months ago
- [CVPR 2022] Official code for "RegionCLIP: Region-based Language-Image Pretraining"☆762Updated last year
- Language-Driven Semantic Segmentation☆784Updated 4 months ago
- Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupe…☆1,002Updated last year
- [NeurIPS 2023] This repo contains the code for our paper Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convoluti…☆314Updated last year
- Official PyTorch implementation of "Extract Free Dense Labels from CLIP" (ECCV 22 Oral)☆440Updated 2 years ago
- Segment-anything related awesome extensions/projects/repos.☆347Updated last year
- Segment Anything combined with CLIP☆340Updated last year
- Grounded Language-Image Pre-training☆2,394Updated last year
- Code release for our CVPR 2023 paper "Detecting Everything in the Open World: Towards Universal Object Detection".☆569Updated 2 years ago
- Painter & SegGPT Series: Vision Foundation Models from BAAI☆2,566Updated 5 months ago
- This is an implementation of zero-shot instance segmentation using Segment Anything.☆311Updated 2 years ago
- Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).☆2,236Updated last year
- Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts☆1,172Updated 4 months ago