jerpelhan/GECO2

Code and implementation guidelines for the paper ✨Counting Anything. Project Page: https://mengqi-lei.github.io/count-anything-projectpage/

Includes the code for training and testing the CountGD++ model from the paper CountGD++: Generalized Prompting for Open-World Counting.

Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.

Use DINOv3’s powerful, self-supervised visual features + YOLOv12’s blazing-fast detection, all in one repo. Whether you have only a few hundred labeled images or a medium-sized dataset, DINOV3-YOLOV12 helps you get better detection accuracy — without sacrificing speed. Great for niche domains, small-data projects, or quick prototyping.

[CVPR 2026] A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps

Multi-Class Few-Shot Semantic Segmentation with Visual Prompts

This is the official implementation of the ECCV'2022 paper "Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation".

DotDotGoose is a free, open source tool to assist with manually counting objects in images

[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence