A Simple-but-effective Baseline for Training-free Class-Agnostic Counting

Yuhao Lin,Haiming Xu,Lingqiao Liu,Javen Qinfeng Shi

IEEE/CVF Winter Conference on Applications of Computer Vision（2025）

引用 0|浏览47

关键词

Prototype,Performance Gap,Counting Accuracy,Foundation Model,Image Encoder,Root Mean Square Error,Training Data,Image Features,Computer Vision,Input Image,Feature Representation,Mean Absolute Error,Bounding Box,Object Of Interest,Counting Method,Computational Overhead,Final Count,Reference Object,Matching Network,Feature Concatenation,Simple Linear Iterative Clustering,Object Counting,Object Proposals,Query Image,Proposal Generation,Visual Model,Benchmark,Performance Gain,K-means

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要