Papers › Scale-Prior Deformable Convolution for Exemplar-Guided Class-Agnostic Counting
Scale-Prior Deformable Convolution for Exemplar-Guided Class-Agnostic Counting
Wei Lin, Kunlin Yang, Xinzhu Ma, Junyu Gao, Lingbo Liu, Shinan Liu, Jun Hou, Shuai Yi, Antoni B. Chan
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.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Object Counting | FSC147 | SPDCN | MAE(test) | 13.51 | #10 of 19 | Archive leaderboard | report |
| Object Counting | FSC147 | SPDCN | MAE(val) | 14.59 | #10 of 19 | Archive leaderboard | report |
| Object Counting | FSC147 | SPDCN | RMSE(test) | 96.80 | #10 of 19 | Archive leaderboard | report |
| Object Counting | FSC147 | SPDCN | RMSE(val) | 49.97 | #10 of 19 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections