A Simple-but-effective Baseline for Training-free Class-Agnostic Counting
IEEE/CVF Winter Conference on Applications of Computer Vision（2025）
Key words
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 Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined