ylqi / Count-Anything
This method uses Segment Anything and CLIP to ground and count any object that matches a custom text prompt, without requiring any point or box annotation.
☆141Updated last year
Alternatives and similar repositories for Count-Anything:
Users that are interested in Count-Anything are comparing it to the libraries listed below
- using clip and sam to segment any instance you specify with text prompt of any instance names☆173Updated last year
- an empirical study on few-shot counting using segment anything (SAM)☆88Updated last year
- Connecting segment-anything's output masks with the CLIP model; Awesome-Segment-Anything-Works☆187Updated 5 months ago
- Combining "segment-anything" with MOT, it create the era of "MOTS"☆152Updated last year
- Grounded Segment Anything: From Objects to Parts☆400Updated last year
- This is an implementation of zero-shot instance segmentation using Segment Anything.☆310Updated last year
- [ACM MM23] CLIP-Count: Towards Text-Guided Zero-Shot Object Counting☆102Updated 11 months ago
- [ICCV2023] Segment Every Reference Object in Spatial and Temporal Spaces☆236Updated 3 weeks ago
- CounTR: Transformer-based Generalised Visual Counting☆106Updated 8 months ago
- SSA + FastSAM/Semantic Fast Segment Anything , or Fast Semantic Segment Anything☆94Updated last year
- Collect some resource about Segment Anything (SAM), including the latest papers and demo☆114Updated last year
- [NeurIPS2023] Code release for "Hierarchical Open-vocabulary Universal Image Segmentation"☆282Updated 11 months ago
- [ICCV2023] VLPart: Going Denser with Open-Vocabulary Part Segmentation☆367Updated last year
- [CVPR 24] The repository provides code for running inference and training for "Segment and Caption Anything" (SCA) , links for downloadin…☆216Updated 5 months ago
- Codebase for the Recognize Anything Model (RAM)☆73Updated last year
- DVIS: Decoupled Video Instance Segmentation Framework☆140Updated 11 months ago
- Recognize Any Regions☆122Updated 2 months ago
- ☆232Updated last month
- (CVPR 2024) Point, Segment and Count: A Generalized Framework for Object Counting☆109Updated 4 months ago
- ☆110Updated 8 months ago
- Combining OwlViT with Segment Anything - Open-vocabulary Detection and Segmentation (Text-conditioned, and Image-conditioned)☆161Updated last year
- [NeurIPS 2023] This repo contains the code for our paper Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convoluti…☆308Updated last year
- ☆47Updated last year
- SAM (Segment Anything Model) for generating rotated bounding boxes with MMRotate, which is a comparison method of H2RBox-v2.☆184Updated last year
- Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation☆402Updated 10 months ago
- ☆134Updated last year
- Image Editing Anything☆113Updated last year
- ☆175Updated last month
- [ICCV 2023] Official implementation of the paper "A Simple Framework for Open-Vocabulary Segmentation and Detection"☆690Updated last year
- A DETR-style framework for open-vocabulary detection (OVD). CVPR 2023☆184Updated last year