Scale-Prior Deformable Convolution for Exemplar-Guided Class-Agnostic Counting
Wei Lin (City University of Hong Kong),* Kunlin Yang (Sensetime Group Limited), Xinzhu Ma (The University of Sydney), Junyu Gao (Northwestern Polytechnical University, Center for OPTical IMagery Analysis and Learning), Lingbo Liu (Hong Kong Polytechnic University), Shinan Liu (SenseTime Group Limited), Jun Hou (SenseTime Group Limited), Shuai Yi (SenseTime Group Limited), Antoni Chan (City University of Hong Kong, Hong, Kong)
The 33rd British Machine Vision Conference
Abstract
Class-agnostic counting has recently emerged as a more practical counting task, which aims to predict the number and distribution of any exemplar objects, instead of counting specific categories like pedestrians or cars. However, recent methods are developed by designing suitable similarity matching rules between exemplars and query images, but ignoring the robustness of extracted features. To address this issue, we propose a scale-prior deformable convolution by integrating exemplars' information, \eg, scale, into the counting network backbone. As a result, the proposed counting network can extract semantic features of objects similar to the given exemplars and effectively filter irrelevant backgrounds. Besides, we find that traditional L2 and generalized loss are not suitable for class-agnostic counting due to the variety of object scales in different samples. Here we propose a scale-sensitive generalized loss to tackle this problem. It can adjust the cost function formulation according to the given exemplars, making the difference between prediction and ground truth more prominent. Extensive experiments show that our model obtains remarkable improvement and achieves state-of-the-art performance on a public class-agnostic counting benchmark. the source code is available at https://github.com/Elin24/SPDCN-CAC.Video
Citation
@inproceedings{Lin_2022_BMVC,
author = {Wei Lin and Kunlin Yang and Xinzhu Ma and Junyu Gao and Lingbo Liu and Shinan Liu and Jun Hou and Shuai Yi and Antoni Chan},
title = {Scale-Prior Deformable Convolution for Exemplar-Guided Class-Agnostic Counting},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0313.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by